© 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. 22-GEMMASCOPE-2-RES-262K
    7. 14042
    Prev
    Next
    INDEX
    Explanations

    exploring and pausing

    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_22_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
     flown
    0.79
     gå
    0.77
    andra
    0.77
     sitter
    0.74
     plong
    0.73
     sitting
    0.73
    isim
    0.72
    躺
    0.71
    处于
    0.71
     viaje
    0.71
    POSITIVE LOGITS
     encountering
    1.27
     pausing
    1.20
     stopping
    1.17
     encounters
    1.14
     Stopping
    1.09
     Eventually
    1.02
     uncovering
    1.01
     culminating
    1.00
    直至
    0.99
    Eventually
    0.95
    Activations Density 0.225%

    No Known Activations