© 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. 223336
    Prev
    Next
    INDEX
    Explanations

    groups and specific entities

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

    difficult circumstances

    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
     Starting
    0.45
    ');
    0.44
     页
    0.44
     )
    0.43
    ways
    0.43
    Trends
    0.42
    <0x0D>
    0.42
     ?
    0.42
     గా
    0.42
     imputation
    0.42
    POSITIVE LOGITS
     luchar
    0.50
    ल्टा
    0.49
     symbolically
    0.46
     Taft
    0.46
     Sulu
    0.45
    geld
    0.45
    chsler
    0.45
    梶
    0.45
    lež
    0.44
     jednou
    0.44
    Activations Density 0.000%

    No Known Activations