© 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. 59223
    Prev
    Next
    INDEX
    Explanations

    http, field, names

    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
    When
    -1.65
    Whether
    -1.59
     Whether
    -1.56
     Sadly
    -1.55
     Perhaps
    -1.54
     when
    -1.54
     Undoubtedly
    -1.52
    》：
    -1.48
     Sometimes
    -1.45
     Probably
    -1.42
    POSITIVE LOGITS
    slightly
    1.42
     takie
    1.39
     cerca
    1.39
     zeer
    1.37
    absolutely
    1.34
    胳
    1.34
    cising
    1.33
    龊
    1.30
    changes
    1.29
     cinq
    1.29
    Activations Density 0.004%

    No Known Activations