© 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. 47343
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    rishnan
    -0.78
     venganza
    -0.75
     sons
    -0.75
    امد
    -0.74
     客厅
    -0.73
    Paste
    -0.72
    nové
    -0.71
     wife
    -0.71
    toks
    -0.71
    kwa
    -0.71
    POSITIVE LOGITS
    claration
    0.88
     Soledad
    0.79
    ступљено
    0.78
    luri
    0.77
     Eras
    0.76
     reCAPTCHA
    0.76
     animes
    0.76
     Wonders
    0.76
    HORE
    0.75
    gisi
    0.75
    Activations Density 0.003%

    No Known Activations