© 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. 31-GEMMASCOPE-2-RES-262K
    7. 32766
    Prev
    Next
    INDEX
    Explanations

    ranking items by order

    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_31_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
    ي
    0.71
    t
    0.64
     estadística
    0.63
    nico
    0.63
    b
    0.63
     classify
    0.62
     Испа
    0.62
    지
    0.61
    ী
    0.58
     partitioned
    0.58
    POSITIVE LOGITS
    et
    0.62
    Rank
    0.57
    ymmetry
    0.56
     rank
    0.54
     Rank
    0.53
     रैंक
    0.53
    icity
    0.52
    、
    0.51
    ِ
    0.50
    ornos
    0.50
    Activations Density 0.018%

    No Known Activations