© 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. 7732
    Prev
    Next
    INDEX
    Explanations

    county administrative divisions

    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
    會有
    -2.72
    簠
    -2.64
    祭り
    -2.61
    鬭
    -2.45
    甃
    -2.38
    鲧
    -2.36
    孖
    -2.34
     They
    -2.33
     כשה
    -2.31
     欣赏
    -2.27
    POSITIVE LOGITS
    <td>
    3.03
    橚
    2.72
     celebre
    2.63
    ２
    2.63
    婓
    2.59
    /
    2.58
    le
    2.52
    ㈰
    2.52
    )
    2.47
    嵛
    2.47
    Activations Density 0.019%

    No Known Activations