© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178419
    Prev
    Next
    INDEX
    Explanations

    completing actions

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

    ASCII art and Moore's Law

    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
    Negative Logits
    ܘ
    0.55
    ariam
    0.53
     dinâmica
    0.45
    agnetic
    0.44
    odigd
    0.44
    ಐ
    0.44
    鳕
    0.44
    বিহীন
    0.43
    eltic
    0.43
    atthakath
    0.42
    POSITIVE LOGITS
    Puede
    0.50
     Importantly
    0.47
     That
    0.46
    Assess
    0.45
    एस
    0.44
    you
    0.44
    打击
    0.44
    s
    0.44
    队友
    0.43
    sü
    0.43
    Activations Density 0.001%

    No Known Activations