© 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. 132615
    Prev
    Next
    INDEX
    Explanations

    email now

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

    unauthorized usage, appropriation

    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
    t
    0.59
     इनके
    0.52
    ambia
    0.48
     shouldn
    0.46
     тў
    0.44
     SONGS
    0.44
     вижу
    0.44
     মিড
    0.44
    ága
    0.43
     डिफरेंट
    0.43
    POSITIVE LOGITS
    ยม
    0.45
    及其
    0.43
    及
    0.41
    篙
    0.40
    Orient
    0.39
    ಸೂ
    0.39
    霊
    0.39
    pping
    0.39
     lus
    0.39
     المقرر
    0.39
    Activations Density 0.000%

    No Known Activations