© 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. 22355
    Prev
    Next
    INDEX
    Explanations

    file paths and directories

    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
    廰
    -1.55
    縵
    -1.38
     fevere
    -1.37
    ⢊
    -1.29
     defire
    -1.29
     olacaktır
    -1.23
    俛
    -1.20
     restent
    -1.20
    妯
    -1.19
     ufe
    -1.17
    POSITIVE LOGITS
    ↵↵
    1.27
     on
    1.25
    ↵↵↵
    1.22
     
    1.20
     április
    1.20
    ↵↵↵↵
    1.11
    ↵↵↵↵↵↵↵↵↵
    1.09
    ผม
    1.08
     "
    1.07
    ↵↵↵↵↵↵
    1.06
    Activations Density 0.073%

    No Known Activations