© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 133910
    Prev
    Next
    INDEX
    Explanations

    collections, processing, preventing

    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
    ("")
    0.46
    企
    0.43
    ::__
    0.38
    (,
    0.38
    periode
    0.37
    scr
    0.37
    大切
    0.37
    arovski
    0.37
    corpor
    0.36
    camera
    0.36
    POSITIVE LOGITS
    🫶
    0.50
    ChatGPT
    0.49
     TikTok
    0.48
     ChatGPT
    0.46
    TikTok
    0.44
    抖音
    0.44
     Axios
    0.44
    🟥
    0.44
    🥹
    0.43
    Ḩ
    0.41
    Activations Density 0.001%

    No Known Activations