© 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. 112104
    Prev
    Next
    INDEX
    Explanations

    corporate, automated, separate, sign

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

    mathematical formula

    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
    tembre
    0.55
    ጀ
    0.52
    专项
    0.51
     изменения
    0.50
    מוש
    0.50
     değişiklik
    0.49
     personer
    0.49
    🤝
    0.48
    چین
    0.48
     Nomination
    0.48
    POSITIVE LOGITS
    ed
    0.55
     hideous
    0.49
     withered
    0.48
     nutritious
    0.48
    。
    0.47
     monster
    0.46
     sensible
    0.46
     weathered
    0.46
     wolf
    0.45
     tasteless
    0.45
    Activations Density 0.001%

    No Known Activations