© 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. 47791
    Prev
    Next
    INDEX
    Explanations

    prefix "mis-"

    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
    镚
    -2.88
    狴
    -2.81
    亹
    -2.80
    亊
    -2.77
    伥
    -2.63
    🗹
    -2.63
    髕
    -2.59
     of
    -2.56
     ktorí
    -2.55
     otras
    -2.53
    POSITIVE LOGITS
    7
    2.75
    ↵
    2.63
    there
    2.61
    的新
    2.56
    6
    2.50
    ",
    2.47
    phylococcus
    2.45
    3
    2.45
     fédé
    2.45
     که
    2.36
    Activations Density 0.010%

    No Known Activations