© 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. 112345
    Prev
    Next
    INDEX
    Explanations

    Manny, Knicks, bump

    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
    ”.
    -3.00
    咈
    -2.77
    The
    -2.73
    “
    -2.70
    ).
    -2.67
    棪
    -2.64
    ”,
    -2.55
    祤
    -2.53
    ญี่ป
    -2.52
    剮
    -2.52
    POSITIVE LOGITS
    ೣ
    3.05
    鱨
    2.86
    ⬮
    2.81
    洇
    2.66
    鼱
    2.64
     réfugiés
    2.63
    
    2.63
    赑
    2.50
    澌
    2.50
    ſu
    2.47
    Activations Density 0.006%

    No Known Activations