© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101791
    Prev
    Next
    INDEX
    Explanations

    looking at someone

    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
    -1.23
     acheteurs
    -1.20
    在这
    -1.19
    />

    -1.16
    はこの
    -1.16
     warmen
    -1.15
    such
    -1.13
    }

    -1.13
    ruptcy
    -1.13
     diketahui
    -1.12
    POSITIVE LOGITS
     where
    1.36
     लिए
    1.22
    一同
    1.21
    かした
    1.10
     from
    1.10
     wondering
    1.09
    shimano
    1.09
     still
    1.05
     dónde
    1.05
     rozwój
    1.05
    Activations Density 0.032%
    No Known Activations