© 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. 13203
    Prev
    Next
    INDEX
    Explanations

    python -m llama

    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
     nói
    2.71
    ÊN
    2.68
    년대
    2.63
     укра
    2.59
    ீக
    2.54
    uldades
    2.53
    ే
    2.52
    து
    2.52
    记住
    2.50
     tàu
    2.48
    POSITIVE LOGITS
    रोवर
    2.70
    yy
    2.60
    orters
    2.47
     '**
    2.43
    പാടി
    2.38
    岖
    2.38
    questa
    2.37
    িক
    2.37
    middels
    2.35
    inen
    2.35
    Activations Density 0.029%

    No Known Activations