© 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. 111405
    Prev
    Next
    INDEX
    Explanations

    visual media or concepts

    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
    ⑭
    0.41
    كبر
    0.39
    otine
    0.38
     Accesat
    0.38
    即可
    0.37
     notebook
    0.37
     дата
    0.37
     consenso
    0.37
    唱歌
    0.36
    =\""
    0.35
    POSITIVE LOGITS
     ফটোগ্রাফ
    0.43
    Histogram
    0.40
    INITIAL
    0.39
    Photography
    0.39
    Magic
    0.38
     تصاویر
    0.38
    armed
    0.38
    igraphic
    0.38
     तस्वीरों
    0.38
    Türk
    0.38
    Activations Density 0.000%

    No Known Activations