© 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. 10483
    Prev
    Next
    INDEX
    Explanations

    data sets and features

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

    image data training split

    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
     торже
    0.61
     المرس
    0.60
    绳
    0.59
    职务
    0.57
    发言
    0.56
     پیغام
    0.55
    Shroud
    0.55
     पूछ
    0.55
    总裁
    0.54
    颁
    0.54
    POSITIVE LOGITS
     preprocessing
    1.06
     dataset
    0.93
     data
    0.91
     sklearn
    0.90
     datasets
    0.89
     samples
    0.89
     multivariate
    0.89
     training
    0.84
    preprocessing
    0.84
    data
    0.82
    Activations Density 0.006%

    No Known Activations