© 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. 31-GEMMASCOPE-2-RES-262K
    7. 100262
    Prev
    Next
    INDEX
    Explanations

    external or internal comparison

    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_31_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
    >=
    0.45
    人数
    0.45
     >>
    0.44
     ",
    0.44
     x
    0.43
    :",
    0.43
     خ
    0.42
     "+
    0.42
    Okay
    0.42
    ：
    0.42
    POSITIVE LOGITS
     wastage
    0.55
     quinine
    0.50
    formaldehyde
    0.47
    šenja
    0.46
    могою
    0.46
     vijj
    0.45
    회의
    0.45
    स्यों
    0.45
    icots
    0.45
    鸪
    0.44
    Activations Density 0.007%

    No Known Activations