© 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. 21242
    Prev
    Next
    INDEX
    Explanations

    quantities of things spoken

    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
     uniquement
    -1.74
    ก็
    -1.63
     também
    -1.54
     también
    -1.52
     nombreux
    -1.49
     nombreuses
    -1.48
     גם
    -1.48
    หลาย
    -1.40
    Зе
    -1.39
     inkább
    -1.38
    POSITIVE LOGITS
     this
    2.09
     when
    2.06
     after
    1.87
     those
    1.80
     that
    1.80
     or
    1.69
     such
    1.57
     who
    1.50
     time
    1.48
     what
    1.48
    Activations Density 0.096%

    No Known Activations