© 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. 112946
    Prev
    Next
    INDEX
    Explanations

    avoiding negative outcomes

    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
    swire
    -1.76
    Ꮏ
    -1.59
    瘊
    -1.32
    ergies
    -1.30
    mability
    -1.28
    푠
    -1.27
    says
    -1.27
     rencont
    -1.23
    zied
    -1.22
    蚧
    -1.20
    POSITIVE LOGITS
     of
    1.68
     also
    1.66
    2
    1.53
    0
    1.52
    8
    1.36
     where
    1.31
    7
    1.27
    4
    1.27
    </em>
    1.26
    9
    1.23
    Activations Density 0.052%

    No Known Activations