© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12244
    Prev
    Next
    INDEX
    Explanations

    quotations, code, and specific locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    KO
    1.78
     Sculpture
    1.72
     ("
    1.68
    ْن
    1.62
     Breed
    1.61
     "
    1.60
     Officials
    1.60
    ↵↵↵
    1.58
     Archives
    1.58
     Gallery
    1.57
    POSITIVE LOGITS
     života
    1.98
    outputPath
    1.81
    InfoHeader
    1.81
    bibfield
    1.78
    readyState
    1.77
     gospodar
    1.74
    PixelRatio
    1.73
    ಿಂತ
    1.73
     божомолу
    1.71
    割合
    1.70
    Activations Density 0.000%

    No Known Activations