© 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. 223269
    Prev
    Next
    INDEX
    Explanations

    iTunes Plus moving services

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

    building analogies and stories

    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
     Pasar
    0.48
     такое
    0.45
     solche
    0.45
     такие
    0.44
     Pittsburg
    0.44
    軌
    0.42
    фект
    0.42
    株式
    0.40
    титься
    0.40
    這樣的
    0.40
    POSITIVE LOGITS
    (%
    0.50
    ae
    0.47
    os
    0.45
    ouette
    0.45
    rotz
    0.44
    radiation
    0.44
    %+
    0.44
    ilangkan
    0.44
    zp
    0.43
     addon
    0.43
    Activations Density 0.000%

    No Known Activations