© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 86734
    Prev
    Next
    INDEX
    Explanations

    CNG, Threshold, UG, cfg, Rock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ってみ
    0.46
    並且
    0.44
     разви
    0.43
    勉
    0.43
     exclude
    0.43
    三人
    0.42
    地
    0.42
     develop
    0.42
    飛行
    0.42
     formulating
    0.42
    POSITIVE LOGITS
    RIDES
    0.54
     misspelled
    0.52
    ratos
    0.52
     buruk
    0.52
     اداکار
    0.51
     fresca
    0.50
     lindos
    0.48
    adiator
    0.48
     बॉलीवुड
    0.48
    /"+
    0.47
    Activations Density 0.000%

    No Known Activations