© 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. 172178
    Prev
    Next
    INDEX
    Explanations

    both sides

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

    japanese origins

    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
    Not in Any Lists

    No Comments

    Negative Logits
     kötü
    0.50
    렜
    0.49
     mechan
    0.48
     Universität
    0.47
     chocolat
    0.46
     Hartree
    0.46
     quay
    0.45
     midday
    0.45
     beak
    0.45
     réseau
    0.45
    POSITIVE LOGITS
    триму
    0.51
     तिथि
    0.50
     個人
    0.48
    ᑎ
    0.48
     ប្រ
    0.48
    celli
    0.47
    cInfo
    0.47
    ponin
    0.47
    snippets
    0.46
     Черка
    0.46
    Activations Density 0.001%

    No Known Activations