© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9126
    Prev
    Next
    INDEX
    Explanations

    numbers and math operations

    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
    Negative Logits
     σ
    0.39
     polarisation
    0.37
     Wittgenstein
    0.36
     ద్వ
    0.36
    Switcher
    0.34
     cereals
    0.33
     riots
    0.33
     cities
    0.32
     rule
    0.31
     γ
    0.31
    POSITIVE LOGITS
    amanho
    0.35
     tỏ
    0.35
    чних
    0.33
    푦
    0.33
     које
    0.33
    atum
    0.33
    さまざまな
    0.32
    晿
    0.31
    یکی
    0.31
    眺
    0.31
    Activations Density 0.006%

    No Known Activations