© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3776
    Prev
    Next
    INDEX
    Explanations

    listing or sequencing actions

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

    The neuron fires strongly on isolated “heading”–style content words that tend to introduce or label a new topic or section in the text.

    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
    ↵
    0.74
     fiabilité
    0.74
    Severity
    0.71
    い
    0.70
     sfida
    0.68
     봐
    0.68
    avourable
    0.66
    ajte
    0.66
    unary
    0.66
     DIFFER
    0.64
    POSITIVE LOGITS
     деятельности
    0.82
     деятельность
    0.81
    Примеча
    0.80
     совершенно
    0.79
     ее
    0.79
    kette
    0.79
    馆
    0.78
     полно
    0.77
     семье
    0.75
    ฉัน
    0.75
    Activations Density 0.000%

    No Known Activations