© 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. 92616
    Prev
    Next
    INDEX
    Explanations

    (Photo by

    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
     план
    -0.73
     parabolic
    -0.69
     saturation
    -0.68
     Saturation
    -0.68
    ovan
    -0.68
    훤
    -0.68
     عشق
    -0.67
     سرطان
    -0.67
    legging
    -0.65
    ELISA
    -0.65
    POSITIVE LOGITS
     Advantage
    0.70
     Delaney
    0.69
     바
    0.69
     przer
    0.69
     Fußball
    0.69
     பா
    0.66
     Mario
    0.65
     Identity
    0.64
     stake
    0.64
    崇
    0.63
    Activations Density 0.050%

    No Known Activations