© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12927
    Prev
    Next
    INDEX
    Explanations

    rates of outcomes

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Scaled
    0.40
    γο
    0.38
    arono
    0.37
    Allocate
    0.36
    Spending
    0.35
    immutable
    0.34
    壤
    0.34
     பெரி
    0.34
    龺
    0.34
    Timestamp
    0.33
    POSITIVE LOGITS
     rates
    1.87
     rate
    1.80
     Rates
    1.63
     taux
    1.61
    率
    1.61
     Rate
    1.57
    Rates
    1.46
     نرخ
    1.45
     RATE
    1.44
     RATES
    1.42
    Activations Density 0.042%

    No Known Activations