© 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. 99240
    Prev
    Next
    INDEX
    Explanations

    multilingual terms for new

    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
     you
    -2.91
     buscando
    -2.66
    ()]);
    -2.34
    những
    -2.33
    archiwizowane
    -2.30
     แต่
    -2.28
    鴴
    -2.27
    ⧠
    -2.23
     ไม่
    -2.23
     trois
    -2.23
    POSITIVE LOGITS
    It
    3.34
     Surprisingly
    3.33
    This
    3.27
    These
    3.19
    There
    3.13
    Almost
    3.11
    Only
    3.11
    Surprisingly
    3.03
    While
    3.02
    When
    2.97
    Activations Density 0.001%

    No Known Activations