© 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. 76754
    Prev
    Next
    INDEX
    Explanations

    sound, health, scaling, slot

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

    ** ** :

    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
    ot
    0.55
    lists
    0.50
    를
    0.50
    lista
    0.46
    enriched
    0.46
    ambio
    0.46
     employment
    0.45
    dated
    0.45
    াশ
    0.44
     फ़ोन
    0.44
    POSITIVE LOGITS
    ازت
    0.46
     回転
    0.44
     entweder
    0.44
    逭
    0.43
     добра
    0.42
    زه
    0.42
    ణ
    0.42
     стре
    0.42
     மாய
    0.42
    ركة
    0.41
    Activations Density 0.001%

    No Known Activations