© 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. 57044
    Prev
    Next
    INDEX
    Explanations

    API calls and versions

    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
     başına
    -0.71
    Babylon
    -0.67
    显得
    -0.66
     Carrot
    -0.65
     convicts
    -0.65
    Roland
    -0.64
    neapolis
    -0.64
     Amon
    -0.64
    oyer
    -0.63
    prüche
    -0.63
    POSITIVE LOGITS
    jarkan
    0.71
    cupa
    0.69
    PCC
    0.68
     جان
    0.67
    orsal
    0.66
    🇻
    0.65
    OPER
    0.64
     LayoutInflater
    0.63
     People
    0.63
     دولت
    0.63
    Activations Density 0.043%

    No Known Activations