© 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-65K
    7. 13113
    Prev
    Next
    INDEX
    Explanations

    means or passage

    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_65k_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
    ি
    0.77
    i
    0.76
    t
    0.73
    ை
    0.72
    ো
    0.71
    ே
    0.69
    ി
    0.66
    ാ
    0.65
    ิ
    0.65
    in
    0.63
    POSITIVE LOGITS
     through
    0.91
     माध्यम
    0.87
    '
    0.87
    通过
    0.86
     melalui
    0.84
     através
    0.84
     через
    0.81
     kroz
    0.80
     intermediaries
    0.80
     través
    0.75
    Activations Density 0.049%

    No Known Activations