© 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. 7437
    Prev
    Next
    INDEX
    Explanations

    code markers and symbols

    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
    ଃ
    -2.05
    ’
    -1.95
    bague
    -1.91
    酝
    -1.87
    :}
    -1.84
    ſters
    -1.84
     mentre
    -1.80
    ∽
    -1.79
     enshr
    -1.77
    ᯾
    -1.74
    POSITIVE LOGITS
     not
    2.13
    "
    1.88
     told
    1.88
    }{
    1.80
    \\
    1.75
     trovano
    1.73
     also
    1.73
    </h2>
    1.73
     nhưng
    1.73
     worked
    1.72
    Activations Density 0.006%

    No Known Activations