© 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. 20788
    Prev
    Next
    INDEX
    Explanations

    XML and SVG code snippets

    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
     `<
    0.44
     <
    0.41
     Total
    0.39
     Def
    0.39
     総
    0.39
    xsd
    0.38
    lep
    0.38
    ("<
    0.37
    的一个
    0.37
    니다
    0.37
    POSITIVE LOGITS
    André
    0.39
     veterinarian
    0.38
    然
    0.38
    FC
    0.37
    扱
    0.37
     ሆ
    0.36
     underlies
    0.36
    Packard
    0.36
    کن
    0.36
     urn
    0.36
    Activations Density 0.001%

    No Known Activations