© 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. 23614
    Prev
    Next
    INDEX
    Explanations

    degrees or comparisons

    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
    cite
    0.47
    }{
    0.45
    itej
    0.45
    ilgan
    0.44
    itative
    0.44
    yrıca
    0.43
     prezident
    0.42
     POLITICAL
    0.42
     پیسې
    0.42
    {
    0.42
    POSITIVE LOGITS
     సరి
    0.51
    OneDrive
    0.47
     Dispatch
    0.45
    র্ডার
    0.44
    百万
    0.43
     én
    0.42
     onboarding
    0.42
    र्स
    0.42
     அது
    0.42
     dispatch
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.