© 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. 69045
    Prev
    Next
    INDEX
    Explanations

    risk, library, sources, on

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

    hypothetical, qualified statements

    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
    Apart
    0.50
    誨
    0.48
     of
    0.47
     *
    0.45
    ものです
    0.45
     (
    0.43
     was
    0.43
     P
    0.43
    移
    0.43
     Duch
    0.43
    POSITIVE LOGITS
    nemidophorus
    0.63
     접속
    0.53
     sportsbook
    0.51
     siglas
    0.48
    स्टिक
    0.48
    껑
    0.47
    nič
    0.46
    වර
    0.45
    চীনের
    0.45
    ানক
    0.44
    Activations Density 0.000%

    No Known Activations