© 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. 11849
    Prev
    Next
    INDEX
    Explanations

    primarily followed by main purpose

    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
    व
    0.58
    м
    0.57
     as
    0.54
    多个
    0.47
    विल
    0.45
    م
    0.45
     multiple
    0.45
     peł
    0.45
     a
    0.42
    MAN
    0.42
    POSITIVE LOGITS
    mainly
    0.80
    mostly
    0.80
     mainly
    0.77
     principalement
    0.75
     Mainly
    0.74
    primarily
    0.74
     primarily
    0.73
     głównie
    0.73
     principalmente
    0.71
     chiefly
    0.71
    Activations Density 0.090%

    No Known Activations