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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 195917
    Prev
    Next
    INDEX
    Explanations

    numbering system

    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
    ್ಯೂ
    0.52
     BULLETIN
    0.45
    tss
    0.44
    美しい
    0.43
    izacin
    0.43
     natürliche
    0.42
    importanza
    0.42
    𝗰
    0.42
     ભગવાન
    0.41
     historische
    0.41
    POSITIVE LOGITS
     gates
    0.50
     builder
    0.46
     uses
    0.44
    Gates
    0.42
     developer
    0.41
     employer
    0.41
    Grid
    0.41
     Gates
    0.41
     unlocks
    0.41
    Legacy
    0.40
    Activations Density 0.002%

    No Known Activations