© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 213201
    Prev
    Next
    INDEX
    Explanations

    after word

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

    role play

    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
     agonists
    0.46
    𝗘
    0.44
     คุณ
    0.43
     sirven
    0.43
     অগ
    0.43
    봇
    0.43
     pumpkin
    0.43
    sette
    0.43
    pumpkin
    0.43
     pumpkins
    0.43
    POSITIVE LOGITS
    身上
    0.55
     منه
    0.52
    ,
    0.50
    发出
    0.49
    慣
    0.49
    交
    0.47
    继
    0.46
    并将
    0.46
    ↵↵
    0.44
     {
    0.44
    Activations Density 0.000%

    No Known Activations