© 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. 428
    Prev
    Next
    INDEX
    Explanations

    two days/nights

    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
    𝚞
    1.88
    <bos>
    1.87
    ினார்
    1.76
    𝚙
    1.67
    𝚜
    1.66
     eee
    1.63
    ‌,
    1.61
     рођено
    1.58
    idemargin
    1.58
    𝚝
    1.58
    POSITIVE LOGITS
    nd
    2.34
    nds
    1.77
    تل
    1.77
    ND
    1.68
    개의
    1.67
    embr
    1.66
    ﮈ
    1.62
    决
    1.59
    تو
    1.58
    𝗻
    1.57
    Activations Density 0.631%

    No Known Activations