© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 25397
    Prev
    Next
    INDEX
    Explanations

    occasion, occupancy, occupy, okay

    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
    รวม
    0.62
    ร่างกาย
    0.57
    $
    0.54
     jeopard
    0.53
    >
    0.51
    $)
    0.50
    σ
    0.49
    ร่าง
    0.48
     enquire
    0.47
    ร
    0.47
    POSITIVE LOGITS
     OCC
    0.74
    is
    0.70
     occasion
    0.68
     Occ
    0.64
     Occupation
    0.61
    Occup
    0.60
    Occ
    0.59
     Occupational
    0.55
     Occup
    0.55
    asional
    0.55
    Activations Density 0.018%

    No Known Activations