© 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-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 677
    Prev
    Next
    INDEX
    Explanations

    there once was a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
    starts
    0.66
    threshold
    0.63
     (
    0.62
     اکت
    0.62
     t
    0.62
     Yeah
    0.61
    foreground
    0.61
     genitals
    0.61
    ulnerability
    0.59
    boosting
    0.58
    POSITIVE LOGITS
    运行时
    0.85
    VideoStream
    0.84
     عزیز
    0.76
    ﹑
    0.75
     ทํา
    0.75
     সেক্রে
    0.73
     পাচ
    0.73
    ScriptInterface
    0.72
     appellee
    0.72
     يعمل
    0.72
    Activations Density 0.001%

    No Known Activations