© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1265
    Prev
    Next
    INDEX
    Explanations

    let me know what you think

    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
     thisComponent
    2.02
     Hä
    1.97
     lệ
    1.92
    𝓌
    1.92
     UserDao
    1.91
    ☦
    1.87
    ḧ
    1.86
    ;%(
    1.86
    ƙ
    1.85
    hiana
    1.84
    POSITIVE LOGITS
    avez
    1.84
    ating
    1.81
    ors
    1.79
    OR
    1.76
    到一个
    1.71
    ्ञ
    1.70
    seekg
    1.67
    re
    1.66
    চনায়
    1.65
    Issues
    1.64
    Activations Density 0.298%

    No Known Activations