© 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. 74499
    Prev
    Next
    INDEX
    Explanations

    heat exchange and dissipation

    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
    ed
    -2.39
    the
    -2.28
     celebrid
    -1.88
    見た
    -1.88
     kompeti
    -1.80
     faſt
    -1.76
    瑰
    -1.73
    ate
    -1.69
    孩子的
    -1.68
    (
    -1.66
    POSITIVE LOGITS
    或者
    2.02
    }
    1.97
     setzen
    1.73
    或
    1.73
    </h5>
    1.66
    QPalette
    1.64
     formidable
    1.63
    genodigd
    1.62
     или
    1.62
    ):
    1.62
    Activations Density 0.019%

    No Known Activations