© 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. 112942
    Prev
    Next
    INDEX
    Explanations

    syndicated columnist editor

    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
    cancelled
    -1.19
    ează
    -1.11
     و
    -1.10
     aktiven
    -1.07
    sibilities
    -1.07
    rojo
    -1.03
    เลข
    -1.03
    átil
    -1.03
    РЭ
    -1.02
     दो
    -1.02
    POSITIVE LOGITS
    </i>
    1.50
    </b>
    1.37
     düşün
    1.15
    -!
    1.12
     nigger
    1.11
    циони
    1.08
     conoscenza
    1.07
     these
    1.06
    }
    1.05
     بوابة
    1.04
    Activations Density 0.078%

    No Known Activations