© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1885
    Prev
    Next
    INDEX
    Explanations

    document page numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nocache
    -0.76
    miste
    -0.75
     SEL
    -0.75
     Requ
    -0.75
     zeroes
    -0.72
     determined
    -0.72
    珞
    -0.72
    isPresent
    -0.71
    αι
    -0.71
     Moslem
    -0.69
    POSITIVE LOGITS
    総
    0.80
    tuned
    0.78
     lemon
    0.75
     باد
    0.74
     दिख
    0.73
    Peggy
    0.73
     graisse
    0.72
    foque
    0.72
    我最
    0.71
    loan
    0.70
    Activations Density 0.084%

    No Known Activations