© 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. 92981
    Prev
    Next
    INDEX
    Explanations

    provided with

    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
    reras
    -0.67
     colla
    -0.66
     sayin
    -0.63
     ruinous
    -0.63
    SPECT
    -0.62
     rượu
    -0.62
     cros
    -0.62
    ==(
    -0.60
     commandant
    -0.60
    Rejection
    -0.60
    POSITIVE LOGITS
     spacing
    0.77
     Jama
    0.73
     AW
    0.71
    senz
    0.71
    ACKNOWLEDGEMENTS
    0.70
     Cymru
    0.70
     Grid
    0.69
    ᠠ
    0.69
    },[
    0.69
     település
    0.68
    Activations Density 0.082%

    No Known Activations