© 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. 13606
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming constructs

    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
     Saltar
    -3.20
    providedIn
    -2.73
    肫
    -2.67
    )
    -2.63
     seus
    -2.45
     mutta
    -2.41
    𝄆
    -2.39
    饉
    -2.38
     perto
    -2.34
    </h6>
    -2.33
    POSITIVE LOGITS
    6
    3.56
    *
    3.30
    8
    3.30
    5
    3.30
    0
    3.06
    2
    3.05
    3
    3.05
    1
    2.98
    ～～～～
    2.97
    4
    2.94
    Activations Density 0.003%

    No Known Activations