© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103634
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    np_acts-logits-general · gemini-2.5-flash-lite

    equals signs in URL parameters, query strings, and variable assignments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     is
    -1.98
     '
    -1.95
     может
    -1.51
    ziali
    -1.46
     каждого
    -1.46
     после
    -1.42
    tolsó
    -1.41
     ".
    -1.40
     In
    -1.39
     <!--
    -1.39
    POSITIVE LOGITS
    -¡
    1.82
    -“
    1.73
    =
    1.73
     vya
    1.68
    *
    1.66
     italie
    1.58
     segun
    1.56
     juntamente
    1.50
     negocia
    1.44
    ཫ
    1.44
    Activations Density 0.045%

    No Known Activations