© 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. 21064
    Prev
    Next
    INDEX
    Explanations

    negation

    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
     and
    -2.91
    8
    -2.39
     This
    -2.31
    7
    -2.27
     precisar
    -2.25
    jaqueta
    -2.23
    9
    -2.20
     tetapi
    -2.20
    4
    -2.19
    What
    -2.14
    POSITIVE LOGITS
    骉
    2.39
    </b>
    2.06
    了下
    2.03
    欒
    2.02
    だったり
    2.00
    蔑
    1.97
    𓐍
    1.93
    愉快
    1.92
    恣
    1.88
     dava
    1.84
    Activations Density 0.015%

    No Known Activations