© 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. 67072
    Prev
    Next
    INDEX
    Explanations

    more

    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
    pography
    -1.48
    lepší
    -1.40
    也会
    -1.39
     meestal
    -1.36
     ktorí
    -1.35
    おはよう
    -1.30
     without
    -1.28
     zorro
    -1.28
    yatı
    -1.28
     leopardo
    -1.27
    POSITIVE LOGITS
     is
    1.49
     see
    1.46
    </b>
    1.44
     Ren
    1.36
     otros
    1.35
    CÓMO
    1.34
     его
    1.34
    不可能
    1.30
     number
    1.30
    ophenol
    1.29
    Activations Density 0.027%

    No Known Activations