© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75203
    Prev
    Next
    INDEX
    Explanations

    sample data and names

    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
    它
    -1.27
    Ν
    -1.14
    rises
    -1.13
     ním
    -1.13
    İZ
    -1.13
    の存在
    -1.12
     głównie
    -1.11
    猛地
    -1.10
     kazak
    -1.10
    moiselle
    -1.10
    POSITIVE LOGITS
     if
    1.42
     new
    1.38
    軼
    1.37
     our
    1.30
    CancelButton
    1.30
    瀉
    1.27
     receive
    1.26
     boletín
    1.24
     unserer
    1.24
     as
    1.24
    Activations Density 0.130%

    No Known Activations