© 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. 191781
    Prev
    Next
    INDEX
    Explanations

    police investigation

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

    exploring themes of

    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
    J
    0.54
    Ahead
    0.52
    M
    0.50
     sdf
    0.49
    MP
    0.48
    drops
    0.48
    SendMessage
    0.48
    Mg
    0.46
     desempenho
    0.46
    '
    0.46
    POSITIVE LOGITS
     Resting
    0.46
     Mont
    0.44
     Roman
    0.44
    ähler
    0.44
     Prohibition
    0.44
     BEC
    0.43
     मैनु
    0.43
     Giro
    0.43
     Française
    0.43
     Kö
    0.42
    Activations Density 0.000%

    No Known Activations