© 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. 85634
    Prev
    Next
    INDEX
    Explanations

    those who

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

    restore browser sessions

    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
     estrés
    0.47
     دهید
    0.47
     quarto
    0.46
     hypergly
    0.46
     hyperglycemia
    0.45
    ﺸ
    0.45
     pyruvate
    0.45
     rhombus
    0.44
    FAULT
    0.43
    xlsx
    0.43
    POSITIVE LOGITS
     불구하고
    0.57
     পড়
    0.52
     虽然
    0.50
    ating
    0.49
     walaupun
    0.49
    ◡
    0.48
     Although
    0.47
     dei
    0.47
     meskipun
    0.46
     जिन्होंने
    0.46
    Activations Density 0.001%

    No Known Activations