© 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. 74846
    Prev
    Next
    INDEX
    Explanations

    case, crumbs, reduction, proposed

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

    qualities and descriptions

    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
    /';
    0.46
    FileDialog
    0.45
    APP
    0.44
    ACKS
    0.42
     bertanggung
    0.41
    Ratings
    0.41
    า
    0.41
     DEVELOPMENT
    0.41
    Bret
    0.40
    AspNet
    0.40
    POSITIVE LOGITS
    فيد
    0.52
     Vem
    0.50
    ობს
    0.49
     eruptions
    0.49
    箒
    0.49
    ஜி
    0.49
     Mercury
    0.47
    ভে
    0.46
    ſe
    0.45
     Bohr
    0.44
    Activations Density 0.000%

    No Known Activations