© 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. 16-GEMMASCOPE-2-RES-262K
    7. 8463
    Prev
    Next
    INDEX
    Explanations

    what something consists of

    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_16_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
     to
    1.28
     an
    1.02
    ки
    1.02
    لي
    0.98
    人
    0.92
    䳕
    0.90
    摖
    0.89
    د
    0.89
    䏍
    0.88
     was
    0.88
    POSITIVE LOGITS
    та
    1.55
    il
    1.30
    ור
    1.22
    ut
    1.20
    l
    1.16
    us
    1.15
    nya
    1.14
    ಮ
    1.13
    ↵↵
    1.12
    is
    1.12
    Activations Density 0.019%

    No Known Activations