© 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. 86428
    Prev
    Next
    INDEX
    Explanations

    My Hero Academiaheroic featsHero Killer

    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
    豋
    -2.84
    ꯸
    -2.72
    ஂ
    -2.47
    鈰
    -2.45
    at
    -2.33
     }
    -2.31
    剮
    -2.25
    </h5>
    -2.23
    ്ട
    -2.20
    d
    -2.20
    POSITIVE LOGITS
    .
    2.95
     betroffen
    2.53
     Oft
    2.44
    ようだ
    2.44
     interactiva
    2.39
     spezi
    2.33
    将他
    2.33
    来る
    2.30
     erkennen
    2.27
    之后
    2.25
    Activations Density 0.005%

    No Known Activations