© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1925
    Prev
    Next
    INDEX
    Explanations

    fillers and pauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arg
    0.64
    ,
    0.64
     to
    0.57
     de
    0.56
    ack
    0.55
    urer
    0.54
    Benzoimidazol
    0.52
    odeficiency
    0.52
    ender
    0.51
    ’
    0.50
    POSITIVE LOGITS
     อืม
    0.77
    em
    0.71
    ث
    0.69
     เอ่อ
    0.68
    for
    0.64
    ان
    0.64
    ه
    0.64
    המ
    0.63
    ت
    0.60
    ু
    0.60
    Activations Density 0.089%

    No Known Activations