© 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. 1936
    Prev
    Next
    INDEX
    Explanations

    a classic riddle

    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
     simplices
    1.01
     κυ
    1.00
    <unused496>
    1.00
    <unused100>
    0.99
    <unused881>
    0.97
    <unused381>
    0.96
     הוא
    0.96
    <unused979>
    0.95
    SpawnEntry
    0.94
    <unused1829>
    0.94
    POSITIVE LOGITS
     ११
    1.02
    ｉ
    1.00
    𝗺
    0.94
    𝗻
    0.93
    ！！！！
    0.92
    ・・・・
    0.92
     ९
    0.92
    Ꭵ
    0.92
     १७
    0.91
    اا
    0.89
    Activations Density 4.621%

    No Known Activations