© 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. 90222
    Prev
    Next
    INDEX
    Explanations

    systems combine with

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

    nearby pressure

    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
    id
    0.53
    dí
    0.49
     investing
    0.48
    meter
    0.48
    এ
    0.47
    t
    0.47
    el
    0.47
    in
    0.46
    আম
    0.46
     logra
    0.46
    POSITIVE LOGITS
     बेसिक
    0.50
     شلون
    0.47
     كيف
    0.47
     εικό
    0.47
     식
    0.46
     باقي
    0.46
     مف
    0.45
     기본적인
    0.45
     አማ
    0.45
    겠지만
    0.45
    Activations Density 0.001%

    No Known Activations