© 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. 1603
    Prev
    Next
    INDEX
    Explanations

    code and programming syntax

    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
     ঢে
    0.91
    Evet
    0.90
     ito
    0.89
    அந்த
    0.89
    anggung
    0.88
     ایسا
    0.87
    爌
    0.86
    <unused501>
    0.86
     له
    0.86
     ack
    0.85
    POSITIVE LOGITS
     etc
    0.86
    等
    0.75
     conspiracies
    0.71
     blog
    0.68
     beaches
    0.66
     western
    0.66
    やお
    0.65
     conspiracy
    0.63
     BAN
    0.62
     markets
    0.62
    Activations Density 0.950%

    No Known Activations