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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1651
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and descriptions

    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_13_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
     choć
    1.06
     industria
    1.02
     будь
    0.94
     отрасли
    0.93
     patria
    0.93
    主流
    0.91
     realista
    0.91
    诟
    0.91
     übernehmen
    0.88
     hiszen
    0.87
    POSITIVE LOGITS
     strange
    0.99
     allegedly
    0.95
     bizarre
    0.93
     apparently
    0.91
     якобы
    0.91
     peculiar
    0.89
     Apparently
    0.89
     नामक
    0.85
     certain
    0.84
     mathematical
    0.84
    Activations Density 2.909%

    No Known Activations