© 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. 12101
    Prev
    Next
    INDEX
    Explanations

    afternoon activities

    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
    ॉ
    2.13
     lej
    2.11
     le
    2.02
    白天
    2.01
    enska
    1.99
     wid
    1.94
    uks
    1.92
    ুষ
    1.90
    csname
    1.90
    قی
    1.88
    POSITIVE LOGITS
    $^{
    2.90
     apunta
    2.43
    .--
    2.34
    Nationality
    2.32
    嬤
    2.31
     accident
    2.31
    晌
    2.30
    sman
    2.29
    scissor
    2.25
     alcanzar
    2.24
    Activations Density 0.017%

    No Known Activations