© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 1611
    Prev
    Next
    INDEX
    Explanations

    information about

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects mentions of an “account” or detailed report/description in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the phrase "detailed account" or similar phrases combining "detailed" with descriptive nouns.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of detailed, authoritative accounts or descriptions, such as an in-depth look, statement, evidence, or views on a subject.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    が発生
    0.65
    ご連絡
    0.62
     mieć
    0.60
    パターン
    0.60
     singolo
    0.59
    ス
    0.57
     NONCLUSTERED
    0.56
    場合は
    0.55
     dział
    0.55
     Alumin
    0.54
    POSITIVE LOGITS
     of
    1.11
     about
    1.05
    关于
    0.95
     về
    0.89
    關於
    0.88
     tentang
    0.86
    about
    0.83
     ofthe
    0.82
     अबाउट
    0.81
     apie
    0.81
    Activations Density 0.000%

    No Known Activations