© 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. 22-GEMMASCOPE-RES-131K
    7. 65157
    Prev
    Next
    INDEX
    Explanations

    mathematical and symbolic notation

    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_22/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
     of
    -1.51
    }\
    -1.16
     (
    -1.16
     venezol
    -1.14
    ,
    -1.13
    </em>
    -1.09
     ,
    -1.09
    ̶
    -1.07
     '*':
    -1.07
     then
    -1.07
    POSITIVE LOGITS
    雰囲
    1.33
    认同
    1.13
     potrebbe
    1.12
    CONTEN
    1.09
     sensibili
    1.06
     bulunabilir
    1.05
    呗
    1.05
     dissi
    1.03
     would
    1.02
     mostrare
    1.02
    Activations Density 0.026%

    No Known Activations