© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14629
    Prev
    Next
    INDEX
    Explanations

    given question, answer, origin

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

    the neuron flags unusually rare or specific content words—especially uncommon nouns, names, and other low-frequency tokens.

    oai_token-act-pair · o4-miniTriggered 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
    ੍
    0.84
     of
    0.80
    ודה
    0.79
     it
    0.79
    ੋਰ
    0.79
    C
    0.78
    ᆭ
    0.77
     easement
    0.75
     אבל
    0.75
    auks
    0.75
    POSITIVE LOGITS
    对称
    0.77
    结合
    0.74
    slidesPer
    0.73
    ürz
    0.72
    selValue
    0.72
     उनका
    0.71
     défini
    0.71
    体会
    0.70
    茟
    0.70
     নত
    0.70
    Activations Density 0.000%

    No Known Activations