© 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. 10-GEMMASCOPE-RES-131K
    7. 67630
    Prev
    Next
    INDEX
    Explanations

    common short word followed by another

    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_10/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
     our
    -2.27
     kteří
    -1.96
     and
    -1.74
    に出演
    -1.71
    快要
    -1.66
    錞
    -1.61
    We
    -1.57
     emanating
    -1.56
     pero
    -1.55
     fís
    -1.52
    POSITIVE LOGITS
    '
    2.08
    _
    2.06
    龶
    1.98
    ;
    1.94
    .
    1.84
     semblables
    1.82
    zied
    1.76
     récents
    1.75
    formatie
    1.74
     datter
    1.72
    Activations Density 0.019%

    No Known Activations