© 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. 17618
    Prev
    Next
    INDEX
    Explanations

    physical objects and states

    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
    k
    0.37
     I
    0.33
    vice
    0.30
     of
    0.30
    da
    0.30
    is
    0.29
    osomes
    0.29
    rt
    0.29
     OV
    0.28
    b
    0.28
    POSITIVE LOGITS
    全都
    0.30
     пове
    0.29
    幇
    0.28
     भोपाल
    0.28
    ла
    0.27
     গ্রহন
    0.25
     เด็ก
    0.25
    วิธีการ
    0.25
    пе
    0.25
     все
    0.25
    Activations Density 0.035%

    No Known Activations