© 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. 128342
    Prev
    Next
    INDEX
    Explanations

    method calls, questions, political titles

    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
    ar
    -2.73
    方がいい
    -2.47
    s
    -2.30
    比起
    -2.25
    ’
    -2.23
    𖥧
    -2.20
    2
    -2.19
    𐐪
    -2.09
    それを
    -2.03
    If
    -2.00
    POSITIVE LOGITS
    ating
    2.27
    ︕
    2.22
    嗵
    2.20
    /
    2.17
    }>
    2.09
    rierten
    2.09
    ๒
    2.09
    躂
    2.09
    吓得
    2.06
    一惊
    2.05
    Activations Density 0.000%

    No Known Activations