© 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. 123543
    Prev
    Next
    INDEX
    Explanations

    not blaming individuals

    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
    舝
    0.55
     পদ্ধতি
    0.54
    IList
    0.52
    驪
    0.49
     похађа
    0.48
    ujjati
    0.48
     اړه
    0.48
    ไม่ใช่
    0.47
    grant
    0.46
     роботи
    0.46
    POSITIVE LOGITS
    нд
    0.46
     (
    0.45
     A
    0.45
     Ча
    0.43
     Tras
    0.43
    нта
    0.43
    henburg
    0.42
    ря
    0.42
     Harsh
    0.42
     tras
    0.42
    Activations Density 0.000%

    No Known Activations