© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 261095
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Beding
    0.55
     Reasoning
    0.49
     Busan
    0.48
     adapté
    0.46
     Paulus
    0.46
    。</
    0.45
     Prudential
    0.45
     konci
    0.45
    ।’
    0.44
     chấm
    0.44
    POSITIVE LOGITS
    棚
    0.48
     axles
    0.44
    гій
    0.43
    殞
    0.42
    rome
    0.42
    SelectedItem
    0.42
    뀌
    0.42
     curves
    0.41
    ன்னை
    0.41
    ણી
    0.41
    Activations Density 0.001%

    No Known Activations