© 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. 112671
    Prev
    Next
    INDEX
    Explanations

    C++ Qt UI code

    np_acts-logits-general · gemini-2.5-flash-lite

    text that appears to be part of GUI or user interface component names, specifically related to text input fields or edit controls in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    3
    -2.70
    2
    -2.63
    (
    -2.61
    "
    -2.58
    大概
    -2.44
    1
    -2.36
    IN
    -2.31
    4
    -2.31
    9
    -2.25
    可以
    -2.23
    POSITIVE LOGITS
     Consejos
    2.42
    遢
    2.38
    噌
    2.36
    回来的
    2.31
     parachoque
    2.28
    勦
    2.28
     Ráp
    2.25
     verbeter
    2.25
    偲
    2.23
     gevoel
    2.16
    Activations Density 0.000%

    No Known Activations