© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14527
    Prev
    Next
    INDEX
    Explanations

    Japanese, Lithuanian, Hindi, English greetings

    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_7_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
    ynthesis
    2.77
    ynthetic
    2.74
    ynd
    2.61
    ystem
    2.55
    繽
    2.46
     PLL
    2.45
     lum
    2.40
    ുതി
    2.36
     مقر
    2.34
    kona
    2.34
    POSITIVE LOGITS
    ような
    2.64
    ∞</
    2.55
    τες
    2.49
    ствовать
    2.40
    popular
    2.38
    rive
    2.37
    べき
    2.30
    rived
    2.28
    様な
    2.28
    Replies
    2.25
    Activations Density 0.003%

    No Known Activations