© 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. 222552
    Prev
    Next
    INDEX
    Explanations

    numbered lists, . , or specific items

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

    biological and philosophical challenges

    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
     Ε
    0.48
    classified
    0.45
    classify
    0.45
     Υ
    0.45
     Saturday
    0.43
     Bolo
    0.43
    toUpperCase
    0.42
     Β
    0.42
     Hobart
    0.42
     Thursday
    0.41
    POSITIVE LOGITS
     streamlines
    0.44
     logiciels
    0.44
    হত্যার
    0.44
     composants
    0.43
     Jednak
    0.43
     знаешь
    0.43
    ണിത്
    0.43
    این
    0.43
    শ
    0.42
    ܡ
    0.42
    Activations Density 0.000%

    No Known Activations