© 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. 34-GEMMASCOPE-RES-131K
    7. 58266
    Prev
    Next
    INDEX
    Explanations

    perfect [noun/descriptor]

    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_34/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
    僦
    -1.13
    ⩕
    -1.13
    ৢ
    -1.08
    ឵
    -1.07
    rofoam
    -1.07
     terá
    -1.05
    }^{-}
    -1.03
    colgroup
    -1.03
    郸
    -1.02
     extravag
    -0.99
    POSITIVE LOGITS
     timing
    1.29
    Just
    1.28
    Also
    1.16
     example
    1.16
    Despite
    1.15
    Perhaps
    1.13
     strangers
    1.12
    Almost
    1.12
    While
    1.11
    Looking
    1.11
    Activations Density 0.017%

    No Known Activations