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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1748
    Prev
    Next
    INDEX
    Explanations

    paths and routes

    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
    ब्ल्यू
    2.44
     norme
    2.38
    িস্টার
    2.35
     definisi
    2.34
    >∞</
    2.32
     sī
    2.31
     leído
    2.30
    েন্ড
    2.27
    RELAND
    2.26
     lê
    2.25
    POSITIVE LOGITS
    दायक
    2.44
    lass
    2.37
    fixes
    2.34
    essions
    2.33
     mắn
    2.31
    m
    2.26
    mir
    2.26
    machen
    2.17
    ्‍य
    2.17
    atk
    2.15
    Activations Density 0.360%

    No Known Activations