© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2474
    Prev
    Next
    INDEX
    Explanations

    providing offers everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_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
    /
    0.67
    eman
    0.63
    ／
    0.61
    spicuous
    0.61
    Chú
    0.61
    izu
    0.60
     Grey
    0.60
     部分
    0.59
    ologue
    0.59
    ²/
    0.59
    POSITIVE LOGITS
     comprehensive
    1.02
     všetky
    0.96
     everything
    0.95
     wszystkie
    0.94
     kaikki
    0.92
    完整的
    0.89
     semua
    0.88
     complete
    0.88
     comprehensively
    0.88
    complete
    0.87
    Activations Density 0.192%

    No Known Activations