© 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. 31-GEMMASCOPE-2-RES-262K
    7. 34818
    Prev
    Next
    INDEX
    Explanations

    technical items, needs, or specifications

    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
    定量
    0.48
    новни
    0.45
    CS
    0.45
    dist
    0.43
     对
    0.42
    यें
    0.42
    状
    0.41
    STAR
    0.41
    க்கள்
    0.41
     行
    0.41
    POSITIVE LOGITS
     Dojo
    0.52
    ພວກເຮົາ
    0.47
    방송
    0.45
     बगैर
    0.44
     inbuilt
    0.43
     conclude
    0.43
     rekao
    0.43
     mencionado
    0.43
    ගේ
    0.43
     apartamentos
    0.43
    Activations Density 0.001%

    No Known Activations