© 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. 7427
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming expressions

    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
     Crem
    0.53
     sería
    0.43
     הייתה
    0.43
     দেখানো
    0.42
     remodeling
    0.42
     permutation
    0.42
    ↵↵
    0.41
     হয়েছিল
    0.41
     vườn
    0.41
     crem
    0.41
    POSITIVE LOGITS
    c
    0.57
    uların
    0.51
    p
    0.49
    ished
    0.47
    le
    0.47
    ardless
    0.46
     сами
    0.46
    liği
    0.45
    avanja
    0.45
     මා
    0.45
    Activations Density 0.006%

    No Known Activations