© 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-65K
    7. 2408
    Prev
    Next
    INDEX
    Explanations

    location and posture

    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_65k_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
    from
    0.31
     إليها
    0.29
    Wasser
    0.25
     زي
    0.24
    𝑓
    0.24
    चलित
    0.23
    formaldehyde
    0.23
     )
    0.23
     erste
    0.23
    زيز
    0.23
    POSITIVE LOGITS
    อยู่ใน
    0.45
     katika
    0.44
     dalam
    0.43
    ใน
    0.40
     trong
    0.39
     squarely
    0.39
     tại
    0.37
     în
    0.36
     ở
    0.35
     atop
    0.35
    Activations Density 0.151%

    No Known Activations