© 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. 69711
    Prev
    Next
    INDEX
    Explanations

    Watch ESPN, pinned Somerset

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

    pseudo-scientific language, harmful content

    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
    oiden
    0.44
     поча
    0.43
     кван
    0.42
     якого
    0.41
     нормы
    0.41
    愣
    0.41
    .{
    0.41
    стъ
    0.40
    ',
    0.40
     maneras
    0.40
    POSITIVE LOGITS
     technically
    0.47
    ログ
    0.46
    डब्ल्यू
    0.44
     DW
    0.44
     cable
    0.44
    ダウン
    0.43
     DVR
    0.43
    ｳ
    0.43
     nw
    0.43
     upland
    0.43
    Activations Density 0.000%

    No Known Activations