© 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. 165396
    Prev
    Next
    INDEX
    Explanations

    tags and permalink separators

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

    realistic expectations

    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
    -
    0.55
    us
    0.55
    ika
    0.52
    {
    0.47
     Piece
    0.47
    '
    0.46
     us
    0.46
    0.46
     Jangan
    0.45
    ey
    0.45
    POSITIVE LOGITS
     realista
    0.55
     পূর্ববাংলা
    0.51
     straining
    0.49
    ুকে
    0.47
     фонд
    0.47
     português
    0.46
     মুক্তিব
    0.46
    糈
    0.46
     realistically
    0.45
    焲
    0.44
    Activations Density 0.001%

    No Known Activations