© 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. 102652
    Prev
    Next
    INDEX
    Explanations

    neglect, negligence, negligible

    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
    ﮕ
    -2.25
     рассказала
    -2.23
    ar
    -2.23
    I
    -2.19
    derdag
    -2.17
     begon
    -2.17
    t
    -2.16
    壜
    -2.14
     onPress
    -2.11
    foreignKey
    -2.09
    POSITIVE LOGITS
    ↵
    4.34
     treacherous
    2.56
     but
    2.47
    ﱠ
    2.33
    鹩
    2.25
    屃
    2.20
    ',
    2.09
     isnt
    1.95
     clutter
    1.92
     Comprometido
    1.88
    Activations Density 0.005%

    No Known Activations