© 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. 265
    Prev
    Next
    INDEX
    Explanations

    sports positions

    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
    S
    0.73
    ه
    0.73
    ה
    0.72
    Sizes
    0.68
    _
    0.68
    ח
    0.68
    שי
    0.68
    (
    0.68
    De
    0.67
    ש
    0.66
    POSITIVE LOGITS
     perif
    0.72
     winged
    0.66
     infringe
    0.63
     त्यांना
    0.62
    atrol
    0.62
     marinated
    0.62
     flimsy
    0.62
    స్ట్
    0.61
     moistened
    0.61
     drib
    0.61
    Activations Density 0.019%

    No Known Activations