© 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. 112625
    Prev
    Next
    INDEX
    Explanations

    listing other categories

    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
    饪
    -2.69
    鼋
    -2.50
     estadounid
    -2.48
     verschillende
    -2.47
    蟊
    -2.44
    at
    -2.42
    きち
    -2.39
    漚
    -2.39
    q
    -2.31
    齮
    -2.31
    POSITIVE LOGITS
    та
    2.97
    ࿚
    2.78
     $
    2.66
     encompassing
    2.59
    。
    2.58
     для
    2.53
     -
    2.47
     ที่
    2.45
    The
    2.39
    餡
    2.39
    Activations Density 0.001%

    No Known Activations