© 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. 2436
    Prev
    Next
    INDEX
    Explanations

    time and distance calculations

    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
     التعامل
    0.45
    ری
    0.41
     হইয়াছিলেন
    0.38
    发表
    0.38
     underlies
    0.38
     Standardization
    0.38
    éments
    0.37
    晠
    0.37
    oyloxy
    0.37
    terminology
    0.36
    POSITIVE LOGITS
     shorten
    0.54
     reciprocal
    0.52
     calculations
    0.50
     calculate
    0.50
     theoretical
    0.49
     calculation
    0.47
    calculate
    0.46
     math
    0.45
     solve
    0.45
     quicker
    0.44
    Activations Density 0.088%

    No Known Activations