© 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. 74124
    Prev
    Next
    INDEX
    Explanations

    itinerary or baritone

    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
     —
    -2.58
    直接
    -2.45
    鴴
    -2.30
    或
    -2.30
    他的
    -2.30
    «
    -2.28
    </td>
    -2.19
    「
    -2.19
    цию
    -2.16
     ſol
    -2.16
    POSITIVE LOGITS
    n
    2.80
    )”
    2.39
    诞生
    2.38
    逦
    2.31
    x
    2.23
    便捷
    2.22
    媖
    2.22
    过后
    2.20
     corriendo
    2.17
    所说的
    2.17
    Activations Density 0.001%

    No Known Activations