© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148839
    Prev
    Next
    INDEX
    Explanations

    comfortable silence or pause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_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
     silent
    0.83
    撳
    0.82
    silent
    0.76
    inare
    0.75
    ໆ
    0.75
     mute
    0.74
    quiet
    0.73
     silently
    0.72
    words
    0.72
    breaks
    0.72
    POSITIVE LOGITS
     সবে
    0.72
     피부
    0.71
    ွဲ
    0.69
     playful
    0.69
     Improves
    0.69
     refle
    0.67
     全
    0.66
     slippery
    0.66
     bag
    0.66
     Optics
    0.66
    Activations Density 0.002%

    No Known Activations