© 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. 99571
    Prev
    Next
    INDEX
    Explanations

    structured format, AI absorb

    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
     license
    0.40
     undergraduate
    0.40
     indicating
    0.39
     library
    0.39
    indic
    0.39
     Frank
    0.39
    N
    0.38
    Ros
    0.38
     Cal
    0.38
    Frank
    0.38
    POSITIVE LOGITS
     अखंड
    0.48
     kiệm
    0.46
     ಸಾಮ
    0.46
    ็ก
    0.44
    ╿
    0.43
    ╽
    0.42
     تنس
    0.41
     ฉาก
    0.41
     پھی
    0.41
    ItemBackground
    0.41
    Activations Density 0.000%

    No Known Activations