© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2675
    Prev
    Next
    INDEX
    Explanations

    getLogger, debug, Settlements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нк
    0.61
     दहा
    0.61
    кви
    0.60
     সদ
    0.59
    েন্টের
    0.59
     जनक
    0.58
    燁
    0.58
    ையாக
    0.58
     energi
    0.58
    нях
    0.58
    POSITIVE LOGITS
    elin
    0.69
     単
    0.63
    ulin
    0.62
     Tun
    0.61
    甘
    0.58
     வடி
    0.58
    obus
    0.57
    Selen
    0.57
     甘
    0.57
    idine
    0.57
    Activations Density 0.225%

    No Known Activations