© 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. 106835
    Prev
    Next
    INDEX
    Explanations

    URLs 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
     Stärke
    -0.80
     Situationen
    -0.78
    onsense
    -0.75
     productions
    -0.72
    prox
    -0.71
    iliki
    -0.71
     supervisory
    -0.71
    ："
    -0.69
    itten
    -0.68
     heats
    -0.67
    POSITIVE LOGITS
    İK
    0.74
    ným
    0.74
    
    0.73
     diri
    0.73
     Symb
    0.70
     sims
    0.69
     Edited
    0.68
     Vineyards
    0.68
     ù
    0.68
    ाय
    0.68
    Activations Density 0.040%

    No Known Activations