© 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. 67677
    Prev
    Next
    INDEX
    Explanations

    setId method

    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
    </h3>
    -2.77
     normalen
    -2.56
    Have
    -2.52
    廕
    -2.52
    葙
    -2.47
     ERSITY
    -2.45
    ية
    -2.39
    絅
    -2.38
    Without
    -2.36
     neuem
    -2.33
    POSITIVE LOGITS
     was
    3.19
    ا
    2.95
    </b>
    2.83
    uminense
    2.56
    ]$
    2.34
    ﮦ
    2.34
    럿
    2.30
     cuales
    2.28
     após
    2.28
    entemente
    2.28
    Activations Density 0.002%

    No Known Activations