© 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. 31740
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
     Coding
    0.40
    块
    0.39
    绘画
    0.38
     painting
    0.38
    缮
    0.38
     coding
    0.37
    coding
    0.36
     ফাইল
    0.36
    单
    0.36
    ℝ
    0.36
    POSITIVE LOGITS
     aggrav
    0.42
     medit
    0.38
    ・・・
    0.38
     sty
    0.38
     worshi
    0.38
    惻
    0.38
    aguars
    0.38
     protect
    0.37
    ത്യ
    0.37
    ئيس
    0.37
    Activations Density 0.000%

    No Known Activations