© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6545
    Prev
    Next
    INDEX
    Explanations

    rewrite this

    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_13_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
     과정
    1.41
    üsse
    1.36
    োষণ
    1.35
    kerja
    1.34
    ര്‍ന്ന്
    1.34
     접
    1.33
     계획
    1.31
     입력
    1.30
     โจทย์
    1.29
     계약
    1.29
    POSITIVE LOGITS
     whatever
    1.05
     lest
    0.97
     cualquiera
    0.93
     anything
    0.92
     Whatever
    0.91
     whence
    0.91
     enige
    0.85
     ANYTHING
    0.85
     whichever
    0.83
    *.
    0.83
    Activations Density 0.166%

    No Known Activations