© 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. 63490
    Prev
    Next
    INDEX
    Explanations

    words starting with und

    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
     nobleman
    -0.73
    全是
    -0.67
     Trieste
    -0.67
    可惜
    -0.66
     exclusivo
    -0.66
    综
    -0.63
     competencias
    -0.62
     Longman
    -0.62
     Pretty
    -0.61
     souvenir
    -0.61
    POSITIVE LOGITS
    desde
    1.00
    Directive
    0.98
    descriptor
    0.97
    deserialize
    0.93
     documentaries
    0.92
     dull
    0.90
     Decreased
    0.90
    dependencies
    0.89
     drapeau
    0.89
    decoded
    0.88
    Activations Density 0.103%

    No Known Activations