© 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. 90822
    Prev
    Next
    INDEX
    Explanations

    Baltic Amber, volleyball, country, number

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

    rainfall after Business Model

    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
    Selon
    0.54
    supervised
    0.52
     élargies
    0.50
    ၎င်း
    0.50
    淒
    0.49
     روایت
    0.49
    ㅉ
    0.48
     আরোপিত
    0.48
     señalado
    0.48
     बल्कि
    0.48
    POSITIVE LOGITS
     Victorian
    0.49
     London
    0.46
     Beatty
    0.45
    edes
    0.45
     Hercules
    0.45
    i
    0.45
     Beech
    0.44
     Water
    0.44
     Advanced
    0.44
     Express
    0.43
    Activations Density 0.000%

    No Known Activations