© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14178
    Prev
    Next
    INDEX
    Explanations

    12345

    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_13_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
     Reyes
    1.66
     Ramirez
    1.58
     رئیس
    1.55
     ‪
    1.54
     הראשון
    1.52
     ‌
    1.51
     Pedro
    1.51
     realizó
    1.50
     Esperanza
    1.49
     ñ
    1.49
    POSITIVE LOGITS
    -/
    1.60
    なども
    1.48
     वगैरह
    1.39
    っぽい
    1.33
    とか
    1.33
    /(
    1.32
     heuristics
    1.27
    やか
    1.27
    あたり
    1.25
    みが
    1.25
    Activations Density 0.051%

    No Known Activations