© 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-16K
    7. 825
    Prev
    Next
    INDEX
    Explanations

    I grabbed for movement

    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_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
     thử
    0.90
    借鉴
    0.83
    试验
    0.79
     erweitert
    0.77
    試し
    0.76
     사용자
    0.73
    穷
    0.73
    眙
    0.72
    培养
    0.71
     thí
    0.71
    POSITIVE LOGITS
     heading
    1.91
     headed
    1.80
     departure
    1.69
    Heading
    1.68
     Heading
    1.63
    Departure
    1.62
     arrive
    1.61
     arriving
    1.61
     return
    1.60
     Departure
    1.59
    Activations Density 0.740%

    No Known Activations