© 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. 12758
    Prev
    Next
    INDEX
    Explanations

    sat perched

    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
    ශ්‍ය
    3.24
    的具体
    2.61
    的网络
    2.59
    اہر
    2.52
    的做法
    2.36
    CMAKE
    2.34
    ःख
    2.33
    的
    2.32
     بيكون
    2.30
     Marte
    2.28
    POSITIVE LOGITS
     предела
    2.11
    ান্ট
    2.01
    ভারে
    1.99
    ন
    1.98
    (*
    1.98
     بیوی
    1.97
     zaw
    1.95
    देशी
    1.95
    sim
    1.94
    વાન
    1.93
    Activations Density 0.033%

    No Known Activations