© 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. 67660
    Prev
    Next
    INDEX
    Explanations

    bunch of

    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
    摃
    -2.67
    ”،
    -2.19
    
    -2.19
    椟
    -2.19
     riscal
    -2.16
    毟
    -2.16
     Jornada
    -2.11
     Wochenende
    -2.09
     repuesto
    -2.03
     Estación
    -2.00
    POSITIVE LOGITS
    y
    2.44
    2
    2.31
    /
    2.20
     (
    2.17
     ("
    2.16
    '
    2.09
    THEN
    2.06
    </b>
    2.05
     «
    2.03
    竟然是
    2.02
    Activations Density 0.006%

    No Known Activations