© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1049
    Prev
    Next
    INDEX
    Explanations

    code definitions

    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_17_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
     दिनांक
    2.56
     /
    2.53
    !!!
    2.53
    /
    2.51
     উক্ত
    2.49
     माननीय
    2.44
    !!
    2.43
    !!!!
    2.40
     মাননীয়
    2.33
    っております
    2.26
    POSITIVE LOGITS
     ­
    2.23
     spokeswoman
    1.98
     ″
    1.95
     plunged
    1.89
    牞
    1.88
    <unused2168>
    1.84
     dogged
    1.83
     amid
    1.82
     spokesman
    1.82
     Islamist
    1.80
    Activations Density 1.648%

    No Known Activations