© 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. 112852
    Prev
    Next
    INDEX
    Explanations

    starting or ending actions

    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
    鹀
    -1.77
     decorativa
    -1.61
     three
    -1.59
    梘
    -1.53
    </h1>
    -1.53
    挥手
    -1.53
     Nutrients
    -1.52
     sugi
    -1.52
     mezi
    -1.51
     которого
    -1.50
    POSITIVE LOGITS
     These
    2.03
    也
    1.95
    4
    1.77
    zação
    1.73
     The
    1.71
    5
    1.71
    8
    1.68
    }$.
    1.68
    2
    1.66
    ípios
    1.63
    Activations Density 0.031%

    No Known Activations