© 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. 6199
    Prev
    Next
    INDEX
    Explanations

    coat with pockets

    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
     أغسطس
    0.84
    ే
    0.83
    WARE
    0.82
    ার
    0.81
    oarece
    0.80
    CORDS
    0.79
    ിൽ
    0.79
     पूरी
    0.79
    ONG
    0.79
    EMENTS
    0.78
    POSITIVE LOGITS
    :
    1.16
    coat
    0.92
     coat
    0.88
    ition
    0.86
    rt
    0.84
    if
    0.80
    her
    0.80
    mon
    0.77
    ride
    0.77
    rad
    0.75
    Activations Density 0.012%

    No Known Activations