© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20581
    Prev
    Next
    INDEX
    Explanations

    Join the

    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
    .
    -2.64
     
    -2.20
    <strong>
    -1.72
    <em>
    -1.66
     Indian
    -1.60
     \
    -1.60
     Free
    -1.59
     ​
    -1.54
     <
    -1.53
    痿
    -1.53
    POSITIVE LOGITS
     or
    1.73
    阋
    1.65
    </b>
    1.64
     січня
    1.61
    おはよう
    1.59
     грудня
    1.59
    Dział
    1.58
    ?”
    1.52
    śl
    1.52
     vaksin
    1.51
    Activations Density 0.006%

    No Known Activations