Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169018
    Prev
    Next
    INDEX
    Explanations

    sharing files and URLs

    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_31_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
    area
    0.50
     몸
    0.50
     antérieur
    0.47
    submission
    0.45
     {})
    0.45
     metallic
    0.44
     previa
    0.43
     보세요
    0.43
     µ
    0.43
     의료
    0.43
    POSITIVE LOGITS
    ون
    0.58
    ين
    0.52
    క్
    0.49
    ائلة
    0.48
    يند
    0.44
    േ
    0.42
    With
    0.41
    Ginger
    0.41
     inconvén
    0.41
    يي
    0.40
    Activations Density 0.006%

    No Known Activations