© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1937
    Prev
    Next
    INDEX
    Explanations

    nuclear activities

    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_17_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
     […]
    1.55
     Diarsipkan
    1.54
    <sup>
    1.50
    ‑
    1.48
    ／
    1.32
    ⁶
    1.30
    <i>
    1.27
     Müller
    1.25
     naïve
    1.25
     Álvarez
    1.24
    POSITIVE LOGITS
     ا
    3.03
    ‪
    2.53
    ‬
    2.49
    Не
    2.41
     herramient
    2.32
     кото
    2.30
     н
    2.26
    И
    2.21
    ส่
    2.19
    Ма
    2.19
    Activations Density 1.588%

    No Known Activations