© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130027
    Prev
    Next
    INDEX
    Explanations

    sandwich

    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_22/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
    <em>
    -1.78
     fabulous
    -1.63
     incredibly
    -1.59
     fantastic
    -1.52
    an
    -1.50
     terrific
    -1.49
    of
    -1.48
     而
    -1.48
    </strong>
    -1.48
     amazing
    -1.45
    POSITIVE LOGITS
    '})
    1.97
    ")}
    1.81
    "},
    1.76
    "));
    1.73
    '},
    1.72
    ܜ
    1.68
     servido
    1.66
    }")
    1.63
    "}
    1.62
    '}
    1.62
    Activations Density 0.009%

    No Known Activations