© 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. 123670
    Prev
    Next
    INDEX
    Explanations

    development trends

    np_acts-logits-general · gemini-2.5-flash-lite

    parts of technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    られた
    0.49
     Buildable
    0.48
    ництво
    0.48
     Variability
    0.48
     Compressor
    0.47
    وض
    0.46
     Cumulative
    0.46
    Ｈ
    0.46
     Collected
    0.46
     Maintains
    0.46
    POSITIVE LOGITS
     devoir
    0.64
     menacing
    0.62
     dogma
    0.59
     patty
    0.59
     menace
    0.59
     perilous
    0.58
    el
    0.55
     taff
    0.55
     chibi
    0.55
     podr
    0.54
    Activations Density 0.000%

    No Known Activations