© 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. 45072
    Prev
    Next
    INDEX
    Explanations

    at least some

    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
    はもちろん
    -1.33
    toja
    -1.33
     zarówno
    -1.30
    </h1>
    -1.27
    </b>
    -1.20
     ACTUALLY
    -1.19
    Vaata
    -1.19
     कई
    -1.19
     persino
    -1.19
     både
    -1.16
    POSITIVE LOGITS
     time
    1.52
     of
    1.45
     who
    1.26
    ofada
    1.22
     Ř
    1.21
    情况下
    1.16
     devised
    1.15
     second
    1.13
     Baş
    1.13
     seem
    1.12
    Activations Density 0.017%

    No Known Activations