© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67573
    Prev
    Next
    INDEX
    Explanations

    abbreviation: definition

    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
     garant
    -1.87
     caricatura
    -1.78
     perak
    -1.68
     ondu
    -1.66
     garan
    -1.63
     pittores
    -1.63
     verbe
    -1.62
     pelu
    -1.62
     tenis
    -1.61
     correcte
    -1.59
    POSITIVE LOGITS
     those
    1.83
     and
    1.73
     many
    1.63
     both
    1.59
     to
    1.56
     S
    1.56
     чаще
    1.52
     but
    1.52
     ,
    1.51
     —
    1.50
    Activations Density 0.000%

    No Known Activations