© 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. 44852
    Prev
    Next
    INDEX
    Explanations

    foundational training

    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
     никогда
    0.63
     жизнь
    0.50
    <unused2157>
    0.48
     jamás
    0.47
    尟
    0.47
     верши
    0.46
     Grundlage
    0.46
    <unused1063>
    0.46
    永远
    0.46
    帜
    0.45
    POSITIVE LOGITS
    ss
    0.52
    III
    0.49
    ned
    0.48
    np
    0.47
    ela
    0.45
    hos
    0.45
    LES
    0.45
    io
    0.45
     ll
    0.44
    nl
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.