© 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. 51470
    Prev
    Next
    INDEX
    Explanations

    complete picture

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

    established API

    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
     천
    0.45
    debounce
    0.43
    hereinafter
    0.42
     *_
    0.41
    ﮢ
    0.41
     shaved
    0.40
     Chaney
    0.40
    prisingly
    0.40
    ㅐ
    0.40
    topology
    0.39
    POSITIVE LOGITS
    甜蜜
    0.48
    uč
    0.48
    Rés
    0.47
     biedt
    0.46
    pèce
    0.46
    زندگی
    0.45
    Été
    0.45
     diskut
    0.45
    uhan
    0.44
     provides
    0.44
    Activations Density 0.000%

    No Known Activations