© 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. 186397
    Prev
    Next
    INDEX
    Explanations

    forms and templates

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

    future, ai, winner, prime, GPU

    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
     تعليم
    0.50
    tä
    0.49
    –
    0.49
     :\
    0.48
    نك
    0.47
     ഉദ്
    0.46
     عرف
    0.46
     ល
    0.46
     الفيزياء
    0.46
     كيلو
    0.45
    POSITIVE LOGITS
     prison
    0.55
     be
    0.51
    ือ
    0.51
     marijuana
    0.49
     torus
    0.49
    つける
    0.49
     prisoner
    0.48
     finder
    0.47
     collection
    0.46
     butterfly
    0.46
    Activations Density 0.000%

    No Known Activations