© 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. 375
    Prev
    Next
    INDEX
    Explanations

    dribbling

    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
     for
    0.77
    Items
    0.59
    getItems
    0.55
    تباه
    0.54
    ן
    0.54
    0.53
    Time
    0.51
     installs
    0.50
     ballots
    0.50
    ИТ
    0.50
    POSITIVE LOGITS
    t
    0.93
     drib
    0.86
    h
    0.78
    l
    0.74
    т
    0.70
    và
    0.65
    and
    0.64
    v
    0.64
    ام
    0.63
    䀼
    0.63
    Activations Density 0.004%

    No Known Activations