© 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. 22412
    Prev
    Next
    INDEX
    Explanations

    acid, board, data

    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
     not
    -1.52
    }
    -1.39
     in
    -1.34
    катерина
    -1.30
     patent
    -1.30
    },
    -1.28
     des
    -1.27
     от
    -1.27
     NOT
    -1.27
     US
    -1.26
    POSITIVE LOGITS
     菇
    1.52
    豋
    1.50
    how
    1.44
     either
    1.38
     why
    1.38
    whether
    1.35
     however
    1.34
     '../../../../
    1.34
    are
    1.29
    Why
    1.29
    Activations Density 0.207%

    No Known Activations