© 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. 31245
    Prev
    Next
    INDEX
    Explanations

    sound artists

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

    bath bombs

    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
     제한
    0.47
    
    0.45
    कामा
    0.44
    medallas
    0.44
     విలువ
    0.43
    valores
    0.43
     நாடுகளில்
    0.43
    腼
    0.43
    तालों
    0.42
     везде
    0.42
    POSITIVE LOGITS
     bijoux
    0.52
     ouverture
    0.49
     brû
    0.48
     extravaganza
    0.46
    instant
    0.46
     idée
    0.46
     Oiseau
    0.46
     instant
    0.45
     exquis
    0.44
     effect
    0.44
    Activations Density 0.000%

    No Known Activations