© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9606
    Prev
    Next
    INDEX
    Explanations

    names starting with Mc

    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
    ↵
    -2.97
    lossians
    -2.78
    鲀
    -2.61
     of
    -2.58
    in
    -2.52
    </strong>
    -2.52
    al
    -2.42
    )$
    -2.42
    畯
    -2.39
    ⽌
    -2.38
    POSITIVE LOGITS
    <
    3.30
     However
    2.80
    "—
    2.48
    鲮
    2.45
     was
    2.44
    *
    2.39
     enjoys
    2.38
    囌
    2.38
    媜
    2.27
     incrí
    2.25
    Activations Density 0.005%

    No Known Activations