© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2688
    Prev
    Next
    INDEX
    Explanations

    suitable qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ρθρο
    1.67
    л
    1.67
     Elwood
    1.60
    щий
    1.58
    хта
    1.54
    на
    1.53
    انب
    1.50
    TouchEvent
    1.49
    х
    1.47
    วก
    1.47
    POSITIVE LOGITS
    cate
    2.14
    bauer
    1.92
     coder
    1.92
    ޤ
    1.86
    tit
    1.75
    oil
    1.75
    𝙡
    1.74
    iunea
    1.74
     ayı
    1.74
    Fallback
    1.71
    Activations Density 0.730%

    No Known Activations