© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62733
    Prev
    Next
    INDEX
    Explanations

    amounts and measurements

    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
    easeOut
    -0.82
     Mab
    -0.78
    ją
    -0.71
     Herman
    -0.71
     Lex
    -0.70
     BON
    -0.70
     Knudsen
    -0.70
     Wit
    -0.69
    gru
    -0.69
     сфере
    -0.69
    POSITIVE LOGITS
     jenem
    0.96
     DCS
    0.87
     thousands
    0.79
    ៛
    0.74
    turnstile
    0.74
     Yunnan
    0.73
     europäischen
    0.72
     eighty
    0.71
    Publik
    0.71
     millennia
    0.70
    Activations Density 0.064%

    No Known Activations