© 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. 26128
    Prev
    Next
    INDEX
    Explanations

    influence and related concepts

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

    sound and detail

    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
     brag
    0.48
     Husky
    0.47
     famiglie
    0.47
    ב
    0.47
    ט
    0.47
     със
    0.46
    ור
    0.45
     עם
    0.45
     husky
    0.44
     optim
    0.44
    POSITIVE LOGITS
     varier
    0.52
     තා
    0.50
    ırs
    0.48
    点的
    0.46
    ᖕ
    0.46
    oye
    0.45
    Influence
    0.45
     влияет
    0.45
     প্রভাব
    0.44
     윤
    0.44
    Activations Density 0.000%

    No Known Activations