© 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. 101373
    Prev
    Next
    INDEX
    Explanations

    valval)val;)val1valgusvalvularvaluse

    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
    鋮
    -2.48
    んでも
    -2.39
     That
    -2.27
    </h1>
    -2.20
    屜
    -2.13
    と感じ
    -2.11
    灕
    -2.09
     ")
    -1.98
     він
    -1.96
    </b>
    -1.95
    POSITIVE LOGITS
    栊
    2.75
    ῞
    2.67
    \
    2.66
    ౮
    2.48
    埽
    2.44
    ཿ
    2.39
    还不错
    2.34
    ть
    2.33
     eer
    2.31
    )
    2.30
    Activations Density 0.004%

    No Known Activations