© 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. 876
    Prev
    Next
    INDEX
    Explanations

    adjective followed by noun

    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
     vultures
    0.65
     GPUs
    0.60
    ను
    0.59
     একজন
    0.59
    কার
    0.58
    ные
    0.57
    ები
    0.56
    의
    0.55
     newsletters
    0.55
     Sunglasses
    0.55
    POSITIVE LOGITS
    ie
    0.74
    ic
    0.71
    į
    0.69
     você
    0.65
    ้า
    0.64
     più
    0.64
     subwoofer
    0.61
    ol
    0.61
     dà
    0.61
     þ
    0.59
    Activations Density 1.505%

    No Known Activations