© 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. 6939
    Prev
    Next
    INDEX
    Explanations

    forming adjectives from roots

    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
    u
    0.85
    ap
    0.83
    ta
    0.83
    ar
    0.80
    ut
    0.74
    as
    0.70
    ff
    0.70
    ha
    0.70
    re
    0.69
    ra
    0.68
    POSITIVE LOGITS
    पणे
    0.71
    0.70
    지
    0.69
     unmistakable
    0.67
    ly
    0.66
     accolade
    0.64
    み
    0.64
    เล
    0.64
     well
    0.61
    ยนต์
    0.61
    Activations Density 0.410%

    No Known Activations