© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1484
    Prev
    Next
    INDEX
    Explanations

    Go standard library packages

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

    Go logging and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鈷
    0.48
     ממ
    0.47
    諗
    0.47
     ከመ
    0.46
    鳳
    0.46
    鉢
    0.45
     निर्देशांक
    0.45
    圓
    0.44
    釣
    0.44
     hình
    0.43
    POSITIVE LOGITS
    golang
    0.86
     chromedp
    0.83
    Gol
    0.72
    logrus
    0.71
    Errorf
    0.68
    WaitGroup
    0.68
    .(*
    0.68
     panicked
    0.66
     Gol
    0.65
     strconv
    0.64
    Activations Density 0.007%

    No Known Activations