© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161250
    Prev
    Next
    INDEX
    Explanations

    matches and non-English words

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

    hackathon

    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
    ă
    0.61
    ı
    0.54
    ‛
    0.54
     though
    0.52
     über
    0.52
    â
    0.52
     weighing
    0.52
     .
    0.51
    ë
    0.50
     paperwork
    0.50
    POSITIVE LOGITS
    對
    0.54
    hình
    0.51
    nsp
    0.48
    Matches
    0.47
    برى
    0.47
    nacht
    0.47
    天
    0.46
    நாள்
    0.46
    matches
    0.46
    دع
    0.46
    Activations Density 0.001%

    No Known Activations