© 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. 11563
    Prev
    Next
    INDEX
    Explanations

    code context markers

    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
     जेव्हा
    0.72
    era
    0.70
    ée
    0.68
     阅读全文
    0.66
    㑓
    0.66
    atorias
    0.65
    AR
    0.64
     när
    0.64
    álni
    0.64
    ä
    0.63
    POSITIVE LOGITS
     clothed
    0.60
     shingles
    0.57
     NGF
    0.57
     horned
    0.56
     equilateral
    0.55
     stride
    0.54
     Gloucestershire
    0.54
     angi
    0.52
     intestines
    0.52
     conceal
    0.52
    Activations Density 0.145%

    No Known Activations