© 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. 130885
    Prev
    Next
    INDEX
    Explanations

    health, safety, religion, descriptions

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

    lists technical details

    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
     HDI
    0.46
     graphene
    0.46
     organize
    0.44
     relocate
    0.44
    vì
    0.44
     تیر
    0.44
    ．
    0.43
    trails
    0.43
    tire
    0.42
    摭
    0.42
    POSITIVE LOGITS
    トラブル
    0.51
    店の
    0.51
    リーム
    0.50
    ージー
    0.50
    願い
    0.49
    আপ
    0.47
    ウォッチ
    0.46
     कामना
    0.46
    ご覧
    0.46
     vostro
    0.46
    Activations Density 0.000%

    No Known Activations