© 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. 170026
    Prev
    Next
    INDEX
    Explanations

    RTX GPUs

    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
     רי
    0.50
     سي
    0.47
     పరి
    0.47
     예배
    0.45
    inf
    0.45
    屒
    0.44
     പ്രദ
    0.44
    ait
    0.43
     ಹಿಂದ
    0.43
    unt
    0.42
    POSITIVE LOGITS
    ภาย
    0.45
     Fulham
    0.45
     Forks
    0.44
     coba
    0.44
    anmar
    0.43
     Compliance
    0.43
     الفور
    0.43
    ک
    0.42
    κολ
    0.42
    ក្ត
    0.42
    Activations Density 0.006%

    No Known Activations