© 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. 2136
    Prev
    Next
    INDEX
    Explanations

    Python `requests` and `random` library usage

    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
     Perkin
    0.64
     Edmunds
    0.64
    vered
    0.64
    鬻
    0.63
    Writes
    0.63
     advisor
    0.62
    ()];
    0.61
     powdered
    0.61
    搧
    0.61
    Way
    0.60
    POSITIVE LOGITS
     necess
    0.77
    NET
    0.76
     compel
    0.72
     नेट
    0.71
    Est
    0.69
     Est
    0.69
    net
    0.68
     reinst
    0.68
     death
    0.65
    swift
    0.64
    Activations Density 0.016%

    No Known Activations