© 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. 57073
    Prev
    Next
    INDEX
    Explanations

    top 500 industrial / specific identifiers

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

    convincing death threat

    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
    ва
    0.51
     Examiner
    0.49
    ваме
    0.49
    كلمنا
    0.46
     examiner
    0.46
    нологи
    0.45
    设备的
    0.45
    弇
    0.45
     चीजों
    0.45
     संभावनाएं
    0.45
    POSITIVE LOGITS
    mathrm
    0.54
    imdb
    0.46
    rite
    0.46
    0.46
     Jiménez
    0.46
     Jimenez
    0.46
    jek
    0.45
    radius
    0.45
    သည်
    0.45
    owned
    0.44
    Activations Density 0.000%

    No Known Activations