© 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. 89108
    Prev
    Next
    INDEX
    Explanations

    officer. editing to small album of easier hormones be cutting

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

    phallic symbols and meanings

    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
    ND
    0.52
    MIL
    0.50
    MILL
    0.50
    MeV
    0.48
    J
    0.48
    William
    0.47
    Signal
    0.46
    Mill
    0.46
    Chief
    0.45
    at
    0.44
    POSITIVE LOGITS
     अदर
    0.47
     ഭൂ
    0.47
    括
    0.46
     ქვე
    0.46
     इंसान
    0.45
    rrr
    0.45
    ”!
    0.45
    dbname
    0.45
     భూ
    0.44
    ingar
    0.44
    Activations Density 0.000%

    No Known Activations