© 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. 10-GEMMASCOPE-RES-131K
    4. 20336
    Prev
    Next
    INDEX
    Explanations

    multi-language digital content

    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
     and
    -3.70
     by
    -3.16
     as
    -3.09
     on
    -3.06
     or
    -2.97
     any
    -2.84
     at
    -2.75
     without
    -2.72
     through
    -2.72
     within
    -2.67
    POSITIVE LOGITS
    甃
    2.78
     horloge
    2.73
    鶫
    2.63
     zoude
    2.58
     verbe
    2.58
    卝
    2.55
     Israël
    2.50
     meub
    2.48
     pérd
    2.48
     acheter
    2.47
    Activations Density 0.019%

    No Known Activations