© 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. 21308
    Prev
    Next
    INDEX
    Explanations

    mailto: links

    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
     personalizadas
    -1.73
    er
    -1.70
     följande
    -1.67
     vitales
    -1.66
     Those
    -1.66
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.66
     potrebbe
    -1.66
     digitais
    -1.65
     möglichen
    -1.65
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.65
    POSITIVE LOGITS
     it
    2.52
     a
    2.23
     to
    2.14
     seperti
    1.84
    since
    1.84
     such
    1.75
     como
    1.73
     kemudian
    1.73
    like
    1.73
    жении
    1.71
    Activations Density 0.014%

    No Known Activations