© 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. 80175
    Prev
    Next
    INDEX
    Explanations

    meal, full, until, represent, is, church, would

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

    undeciphered geometry or pending states

    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
     வண்ண
    0.46
     Acet
    0.46
     शब्
    0.44
    runken
    0.44
    ύ
    0.44
    陆
    0.43
    વાનું
    0.43
    জন
    0.43
     मोटर
    0.42
    สร
    0.42
    POSITIVE LOGITS
    u
    0.57
    ties
    0.55
    userdata
    0.49
    a
    0.49
     ..,
    0.49
    os
    0.48
     .
    0.48
    .}
    0.48
    чении
    0.47
     budget
    0.46
    Activations Density 0.000%

    No Known Activations