© 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. 14949
    Prev
    Next
    INDEX
    Explanations

    pygame.init() and display setup

    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
     was
    1.52
     the
    1.41
     and
    1.39
     벗
    1.38
     は
    1.34
     그리고
    1.34
    ”
    1.32
    で
    1.30
    만
    1.29
    에서
    1.28
    POSITIVE LOGITS
    ozu
    1.68
    nums
    1.59
    िमी
    1.59
    ooi
    1.49
    オク
    1.49
    ربعة
    1.47
    CharField
    1.45
    𒈗
    1.43
    nu
    1.42
    gstatic
    1.38
    Activations Density 0.000%

    No Known Activations