© 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. 73276
    Prev
    Next
    INDEX
    Explanations

    any, anything, whatsoever

    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
     certains
    -1.52
     Mbps
    -1.23
    鉏
    -1.15
     niektórych
    -1.13
    tamment
    -1.09
    hält
    -1.09
     alguns
    -1.09
    perhaps
    -1.09
    zzazione
    -1.05
     Municipalidad
    -1.05
    POSITIVE LOGITS
     any
    3.50
     anything
    2.50
    任何
    2.39
     whatsoever
    2.23
     cualquier
    2.19
     qualquer
    2.11
     ANY
    2.08
    有任何
    2.08
     anyone
    1.98
     or
    1.82
    Activations Density 0.074%

    No Known Activations