© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13902
    Prev
    Next
    INDEX
    Explanations

    dystop, Ish, MPa

    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
    疍
    -2.84
     caricatura
    -2.78
    ܆
    -2.66
     homage
    -2.52
    进入了
    -2.47
    が付いて
    -2.45
    鉏
    -2.44
    粜
    -2.42
     the
    -2.41
    罽
    -2.41
    POSITIVE LOGITS
    ة
    3.23
    ing
    3.11
    瀟
    2.52
    .”
    2.50
    All
    2.45
    ಿ
    2.41
     perceptive
    2.28
    爰
    2.20
    It
    2.20
    ひとつ
    2.19
    Activations Density 0.019%

    No Known Activations