© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39288
    Prev
    Next
    INDEX
    Explanations

    daily happy hour

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

    compliance and summaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     analysing
    0.41
    ;%(
    0.41
     diesem
    0.40
     subscribing
    0.39
     Studying
    0.39
     معیار
    0.39
     INDUSTRIES
    0.38
     weiteren
    0.38
    ff
    0.38
    tugraz
    0.38
    POSITIVE LOGITS
     인한
    0.46
    کنندگان
    0.44
    長さ
    0.43
    ɦ
    0.41
     объ
    0.41
    សូម
    0.41
    カン
    0.41
    हिंद
    0.40
    ن
    0.40
    用水
    0.39
    Activations Density 0.000%

    No Known Activations