© 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. 114484
    Prev
    Next
    INDEX
    Explanations

    place names and locations

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

    issue and its resolution

    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
    参
    0.49
     catalysts
    0.48
    folds
    0.48
    ogenous
    0.48
     offences
    0.48
     peculiarities
    0.47
     पांच
    0.47
    Margins
    0.46
     simplices
    0.46
    捛
    0.46
    POSITIVE LOGITS
     penggunaan
    0.55
    ர்
    0.49
    বাস
    0.48
     momento
    0.48
     ziua
    0.48
    ব্যবহার
    0.47
    ۍ
    0.46
    Î
    0.46
     continuidade
    0.46
     relatório
    0.46
    Activations Density 0.000%

    No Known Activations