© 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. 112451
    Prev
    Next
    INDEX
    Explanations

    something appears in context

    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
    圌
    -3.42
    蠖
    -3.09
    刧
    -2.89
    ৢ
    -2.86
    ⩴
    -2.81
    ㋛
    -2.81
    櫺
    -2.78
    笵
    -2.78
    蹰
    -2.77
    ☫
    -2.75
    POSITIVE LOGITS
     Seems
    3.22
    ࿚
    3.02
     Trying
    2.95
     Actually
    2.94
     With
    2.89
     Apparently
    2.86
     Keeping
    2.77
     Surprisingly
    2.75
     Possibly
    2.70
     Somehow
    2.69
    Activations Density 0.027%

    No Known Activations