© 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. 10887
    Prev
    Next
    INDEX
    Explanations

    physically + [state or action]

    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
    olahan
    -2.11
    Â
    -2.05
    </h3>
    -2.05
    虓
    -2.02
    ⽥
    -2.00
     abur
    -1.91
    ⚌
    -1.91
     encan
    -1.91
    a
    -1.87
    ía
    -1.86
    POSITIVE LOGITS
    '
    2.89
     ,‬
    2.38
     zorgt
    2.36
     brengt
    2.30
    圌
    2.25
     Inſ
    2.20
    笈
    2.19
     fährt
    2.17
    柒
    2.11
     lijkt
    2.09
    Activations Density 0.010%

    No Known Activations