© 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. 11442
    Prev
    Next
    INDEX
    Explanations

    individual differences and variations

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

    varies based on context

    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
    嘖
    0.43
     tiền
    0.43
     dinero
    0.42
    ăzi
    0.41
    DeleteItem
    0.40
     کارت
    0.40
    แหล่ง
    0.40
     идеи
    0.40
    ưở
    0.39
     ଯ
    0.39
    POSITIVE LOGITS
     variability
    0.96
     unique
    0.91
     individual
    0.90
     Variability
    0.90
     individualized
    0.89
     varies
    0.89
    individual
    0.88
     индивидуа
    0.87
     individuale
    0.87
     variations
    0.86
    Activations Density 0.230%

    No Known Activations