© 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. 10-GEMMASCOPE-RES-131K
    7. 21292
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

    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
     HttpNotFound
    -1.45
     なる
    -1.33
     unseren
    -1.28
     вона
    -1.28
     unserer
    -1.26
    //
    -1.26
    她就
    -1.25
    鱟
    -1.23
     eighteen
    -1.22
     sixteen
    -1.22
    POSITIVE LOGITS
     that
    2.47
     einzigartigen
    1.68
     its
    1.41
     verrez
    1.40
     swoją
    1.37
    dieron
    1.28
    batsman
    1.27
    oğlu
    1.26
     wichtigsten
    1.24
     tecnologias
    1.24
    Activations Density 0.003%

    No Known Activations