© 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. 51065
    Prev
    Next
    INDEX
    Explanations

    crafts and hobbies

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

    bizarre music and style

    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
    思考
    0.54
    椪
    0.46
    携
    0.45
    বিস্তারিত
    0.44
    后面
    0.43
    。\
    0.43
    財務
    0.43
    これも
    0.42
     pensado
    0.42
    𒁳
    0.42
    POSITIVE LOGITS
     minif
    0.45
     inhabitants
    0.43
     Worship
    0.43
     liberally
    0.43
     explored
    0.43
     uży
    0.43
     nuovi
    0.43
    峤
    0.42
     pearl
    0.42
     नए
    0.41
    Activations Density 0.000%

    No Known Activations