© 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. 195559
    Prev
    Next
    INDEX
    Explanations

    legal consequences or safety risks

    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
     ಒತ್ತ
    0.43
    ="#
    0.42
    los
    0.39
     Chall
    0.39
     phú
    0.38
    ạt
    0.38
    luor
    0.38
     biops
    0.36
    ául
    0.36
    spann
    0.36
    POSITIVE LOGITS
     Вели
    0.40
     добавлен
    0.37
    σκεται
    0.37
     ED
    0.37
     강화
    0.37
     arke
    0.36
    甕
    0.36
    getLocal
    0.36
     ಉಪ
    0.35
     внесен
    0.35
    Activations Density 0.006%

    No Known Activations