© 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. 35252
    Prev
    Next
    INDEX
    Explanations

    stockbrokers, Internet, calculate total

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

    program instructions

    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
    RenderTarget
    0.46
     wears
    0.41
    SqlClient
    0.41
    推送
    0.40
     OS
    0.39
    Anime
    0.39
    ท
    0.39
    Mitsubishi
    0.38
    yeon
    0.38
    firestore
    0.38
    POSITIVE LOGITS
     linha
    0.43
     BENEF
    0.43
    
    0.42
     linea
    0.40
     Universidade
    0.40
    రాలు
    0.39
     Benefit
    0.38
    стру
    0.38
     beneficios
    0.37
     Übers
    0.36
    Activations Density 0.002%

    No Known Activations