© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3183
    Prev
    Next
    INDEX
    Explanations

    title

    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
     DAY
    1.73
    ClNO
    1.66
    
    1.64
     套
    1.62
     xī
    1.60
    탉
    1.59
    ඹ
    1.59
    ώ
    1.58
    地的
    1.58
     时尚
    1.58
    POSITIVE LOGITS
    able
    1.25
    ogenic
    1.25
    ing
    1.18
    ed
    1.15
    يها
    1.11
    es
    1.09
    етки
    1.08
    ها
    1.08
    igation
    1.07
    еты
    1.07
    Activations Density 0.129%

    No Known Activations