© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13983
    Prev
    Next
    INDEX
    Explanations

    proper nouns and place names

    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
     ď
    1.73
    多次
    1.61
     NS
    1.57
     sited
    1.51
    க்ஸாண்ட
    1.51
    ұ
    1.49
    怔
    1.48
    ﮢ
    1.47
    ᆻ
    1.47
    ヤ
    1.45
    POSITIVE LOGITS
     shoes
    1.73
    asie
    1.61
     kids
    1.60
    iego
    1.58
    瘪
    1.57
     thoughts
    1.57
    ़
    1.57
    jete
    1.53
     tomatoes
    1.52
    aitan
    1.52
    Activations Density 0.265%

    No Known Activations