© 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. 106741
    Prev
    Next
    INDEX
    Explanations

    software components and licensing

    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
     zwierząt
    -0.74
    كرت
    -0.69
     вкусно
    -0.69
    ിക
    -0.68
     gum
    -0.67
     enth
    -0.66
    株式
    -0.66
     Anth
    -0.65
     еле
    -0.65
    돈
    -0.65
    POSITIVE LOGITS
     sulfur
    0.75
    じ
    0.71
     Ai
    0.68
     Trav
    0.68
    consulting
    0.67
    querade
    0.66
     insecticides
    0.64
     sulphur
    0.63
     wersji
    0.63
    拍
    0.63
    Activations Density 0.066%

    No Known Activations