© 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. 227344
    Prev
    Next
    INDEX
    Explanations

    celebrated, married, during, will, before, service, affect

    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
     દવા
    0.52
    펩
    0.47
    티
    0.47
     ефектив
    0.46
    fdPar
    0.46
     pollute
    0.46
     પ્રાપ્ત
    0.45
    FileLine
    0.45
     وع
    0.44
    
    0.44
    POSITIVE LOGITS
     viya
    0.52
     journeys
    0.50
    üsseldorf
    0.50
     catches
    0.50
     nü
    0.50
    issä
    0.50
    k
    0.49
     tds
    0.49
    vaa
    0.49
    जगी
    0.49
    Activations Density 0.001%

    No Known Activations