© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14993
    Prev
    Next
    INDEX
    Explanations

    code syntax markers

    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
    -
    -1.93
     their
    -1.56
     Infór
    -1.48
    noted
    -1.48
     the
    -1.48
     späteren
    -1.35
    當天
    -1.34
    を作り
    -1.34
    を終
    -1.34
    événement
    -1.34
    POSITIVE LOGITS
     和
    1.88
    我们
    1.73
    )}
    1.62
    $}
    1.60
    𝐒
    1.56
    เรา
    1.52
     and
    1.52
    },
    1.49
    0
    1.49
    ?”
    1.48
    Activations Density 0.015%

    No Known Activations