© 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. 47335
    Prev
    Next
    INDEX
    Explanations

    software license agreements

    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
    Сыртқы
    -0.83
    rede
    -0.76
    HMAC
    -0.69
     daer
    -0.68
    vičius
    -0.68
    snake
    -0.68
    acres
    -0.67
     Weeks
    -0.67
     Monaten
    -0.67
    DEAR
    -0.66
    POSITIVE LOGITS
     spinner
    0.68
     designation
    0.68
     Collaborative
    0.66
     subsp
    0.65
     fairs
    0.64
    ลอง
    0.63
     بالس
    0.63
    سرد
    0.62
    Lors
    0.62
     guest
    0.62
    Activations Density 0.055%

    No Known Activations