© 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. 113233
    Prev
    Next
    INDEX
    Explanations

    identify your line

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

    rare human unique instances

    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
     نقدم
    0.48
     personalizar
    0.46
     تحتاج
    0.45
    فع
    0.44
    Ferg
    0.43
    ایت
    0.43
    Wells
    0.42
    鎳
    0.42
     efet
    0.41
    开设
    0.41
    POSITIVE LOGITS
     equality
    0.54
    в
    0.52
    affaires
    0.50
     затруд
    0.50
    anyahu
    0.49
     equitable
    0.49
    égalité
    0.48
     равно
    0.47
    ónde
    0.46
    ór
    0.46
    Activations Density 0.003%

    No Known Activations