© 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. 236918
    Prev
    Next
    INDEX
    Explanations

    services and topics

    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
    ウス
    0.47
    完成
    0.46
    ช่วย
    0.46
    鏤
    0.45
    乂
    0.45
    体验
    0.45
     Pistons
    0.43
    shapes
    0.42
    できます
    0.42
    開業
    0.42
    POSITIVE LOGITS
     rr
    0.53
     খরচ
    0.50
     bahwa
    0.49
     that
    0.48
    unakan
    0.47
    L
    0.47
    Publications
    0.47
    :",
    0.47
     publicação
    0.47
     alcohol
    0.46
    Activations Density 0.000%

    No Known Activations