© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20753
    Prev
    Next
    INDEX
    Explanations

    Víctor, Volt, Gli, carbohydrate, Jimi, UNIX, LogFile

    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
    </sup>
    -3.00
    脔
    -2.72
    酲
    -2.72
    朊
    -2.69
    }{
    -2.59
    趼
    -2.56
    .
    -2.56
    砒
    -2.50
    蕺
    -2.45
    也许
    -2.44
    POSITIVE LOGITS
    there
    3.41
    </h3>
    2.88
    遢
    2.47
     There
    2.47
     When
    2.47
    …..
    2.44
     labelled
    2.33
     
    2.31
     comerci
    2.31
     Ministro
    2.31
    Activations Density 0.011%

    No Known Activations