© 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. 123723
    Prev
    Next
    INDEX
    Explanations

    description of process or function

    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
     anglais
    0.55
     człowie
    0.47
     inglese
    0.47
     Inglaterra
    0.46
    뮤
    0.46
    kadang
    0.46
     usato
    0.46
    nią
    0.44
    뺨
    0.43
     nél
    0.43
    POSITIVE LOGITS
    Testing
    0.50
     प्र
    0.48
     Procurement
    0.47
    lost
    0.46
    ̣i
    0.45
     program
    0.44
     Nagar
    0.44
     insights
    0.44
     Testing
    0.43
     fields
    0.43
    Activations Density 0.001%

    No Known Activations