© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48197
    Prev
    Next
    INDEX
    Explanations

    descriptions and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dah
    0.48
     perju
    0.47
     naughty
    0.47
     unbeatable
    0.46
    정
    0.45
     unorthodox
    0.44
     resent
    0.43
     dah
    0.42
     graduellement
    0.42
     போராட்ட
    0.42
    POSITIVE LOGITS
     Load
    0.55
    ar
    0.53
    en
    0.51
     Vis
    0.51
    a
    0.48
    Vis
    0.47
     Indicator
    0.47
    Load
    0.47
    getResource
    0.46
    or
    0.45
    Activations Density 0.004%

    No Known Activations