© 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. 13235
    Prev
    Next
    INDEX
    Explanations

    import pyplot as

    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
    ного
    2.54
    𝐳
    2.49
    kaç
    2.35
    𝐮
    2.35
    𝐨
    2.34
    𝐁
    2.31
    𝐌
    2.30
    ე
    2.26
    勳
    2.22
    𝐓
    2.21
    POSITIVE LOGITS
    =’
    3.22
    н
    2.99
    нский
    2.97
    ン
    2.67
    กว่า
    2.66
    ′-
    2.64
    -‘
    2.61
    ozygous
    2.59
    △
    2.59
    нской
    2.56
    Activations Density 0.019%

    No Known Activations