© 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. 163483
    Prev
    Next
    INDEX
    Explanations

    locations, objects, and abstract concepts

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

    open-weights decoder-only model

    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
     répart
    0.50
     jaki
    0.47
    نيف
    0.46
     ich
    0.46
    ള്
    0.46
    erville
    0.45
    튕
    0.43
     jakim
    0.42
     Racing
    0.42
     racing
    0.42
    POSITIVE LOGITS
    s
    0.54
     돌아
    0.52
    Tomas
    0.49
     活動
    0.49
    Desde
    0.46
    Totals
    0.45
     સંપૂર્ણ
    0.45
     वोटों
    0.45
    Полу
    0.44
    SIP
    0.44
    Activations Density 0.001%

    No Known Activations