© 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. 40-GEMMASCOPE-2-RES-262K
    7. 15697
    Prev
    Next
    INDEX
    Explanations

    comparative thresholds

    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_40_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
    گیز
    0.34
    Chin
    0.34
    "]).
    0.34
    儕
    0.33
    バランス
    0.33
    選項
    0.33
    एनएल
    0.32
    ।''
    0.32
    僞
    0.31
    ívá
    0.31
    POSITIVE LOGITS
     than
    1.31
    than
    1.00
     niż
    0.96
     kuin
    0.91
     чем
    0.89
     än
    0.87
     Than
    0.86
    กว่า
    0.84
     decât
    0.84
    Than
    0.82
    Activations Density 0.014%

    No Known Activations