© 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. 43813
    Prev
    Next
    INDEX
    Explanations

    names starting with McG

    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
    他自己
    -2.81
    他要
    -2.80
    潆
    -2.70
     Their
    -2.61
    ar
    -2.58
     Its
    -2.44
    2
    -2.34
    including
    -2.33
    他有
    -2.33
     It
    -2.31
    POSITIVE LOGITS
    }$
    3.02
    ."
    2.67
    дәбият
    2.58
    }=
    2.50
    考えて
    2.39
    ación
    2.39
    ère
    2.30
    鼷
    2.30
    </>
    2.30
     viele
    2.28
    Activations Density 0.005%

    No Known Activations