© 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. 129063
    Prev
    Next
    INDEX
    Explanations

    asking if

    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
     दोनों
    -1.86
     Eröffnung
    -1.84
     vermutlich
    -1.83
    Both
    -1.81
     Entire
    -1.80
     rất
    -1.79
    ⅙
    -1.78
    ⅕
    -1.77
    不管是
    -1.77
     Fällen
    -1.76
    POSITIVE LOGITS
     you
    2.27
    2
    2.09
    and
    1.96
     noong
    1.69
     baada
    1.68
     vůbec
    1.64
    6
    1.61
     caracter
    1.56
     inaweza
    1.56
     покри
    1.55
    Activations Density 0.032%

    No Known Activations