© 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. 133354
    Prev
    Next
    INDEX
    Explanations

    park, City, Player, silhouette

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

    creating or starting

    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
    V
    0.55
    ;
    0.50
    K
    0.48
    J
    0.47
    حي
    0.47
    سری
    0.46
    POS
    0.46
    ނ
    0.46
    v
    0.46
    C
    0.45
    POSITIVE LOGITS
     पढ़ें
    0.54
     کا
    0.52
     prek
    0.48
    reflective
    0.48
     புரி
    0.47
    嚗
    0.47
     maatau
    0.45
     منظر
    0.45
    闂
    0.45
     inactivació
    0.44
    Activations Density 0.000%

    No Known Activations