© 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. 203947
    Prev
    Next
    INDEX
    Explanations

    Error, show, template, del, bv, dragons, staff, foto, Japanese

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

    math, historical context, explanations, code

    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
    Ს
    0.50
    .
    0.49
    Ფ
    0.48
     LEN
    0.48
     ribosomes
    0.46
    Col
    0.45
    amu
    0.45
    Lena
    0.44
    WTO
    0.44
    του
    0.44
    POSITIVE LOGITS
     डिस्क्रिप्शन
    0.52
     じゃん
    0.48
    １
    0.47
     Equation
    0.47
    はじ
    0.47
     इक्वेशन
    0.46
     जंगली
    0.46
     公式
    0.46
     trigonometry
    0.46
    น้ำ
    0.45
    Activations Density 0.000%

    No Known Activations