© 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. 45044
    Prev
    Next
    INDEX
    Explanations

    university and department names

    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
    |"
    -1.85
    錾
    -1.84
    ܆
    -1.80
     Formule
    -1.79
    ########.
    -1.79
     bronz
    -1.73
     enceinte
    -1.69
    憷
    -1.67
    -1.66
     débuts
    -1.66
    POSITIVE LOGITS
     that
    2.00
     like
    1.73
     in
    1.73
     at
    1.66
     or
    1.59
    ↵↵
    1.52
     it
    1.51
     more
    1.51
    عادة
    1.48
     of
    1.46
    Activations Density 0.068%

    No Known Activations