© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3049
    Prev
    Next
    INDEX
    Explanations

    tales to be told

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Frances
    1.84
    ᕗ
    1.77
     المؤ
    1.77
    жу
    1.76
     Dominican
    1.74
     Callback
    1.70
     Fanny
    1.68
     Rue
    1.67
     Equival
    1.67
    评
    1.66
    POSITIVE LOGITS
    atein
    0.88
    astal
    0.68
    imd
    0.68
    ocyte
    0.61
    plasma
    0.58
     comprehensively
    0.56
    ousand
    0.56
    Productos
    0.55
    icle
    0.55
    heer
    0.54
    Activations Density 0.055%

    No Known Activations