© 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. 12055
    Prev
    Next
    INDEX
    Explanations

    class initializers

    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
    ্লাহ
    3.02
    ্ডিং
    2.75
    joen
    2.68
    ંગી
    2.65
    <bos>
    2.64
    턴
    2.59
    ্ডার
    2.56
    dding
    2.54
    पिक्सल
    2.54
    cipher
    2.54
    POSITIVE LOGITS
    s
    3.93
    بھ
    2.97
    潢
    2.91
    の頃
    2.91
    ะ
    2.86
    ের
    2.86
    깐
    2.83
    র
    2.77
    infested
    2.77
    fourths
    2.76
    Activations Density 0.008%

    No Known Activations