© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11278
    Prev
    Next
    INDEX
    Explanations

    python code list operations

    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
    ุย
    1.14
    뒷
    1.06
    MathML
    1.04
    保障
    0.97
     뒷
    0.96
     Stamp
    0.94
    쫄
    0.93
    Aspect
    0.91
     փ
    0.91
     FRONT
    0.91
    POSITIVE LOGITS
     normale
    1.43
     normales
    1.19
     Normal
    1.19
     असामान्य
    1.15
     deviates
    1.10
     recommended
    1.09
    normal
    1.09
     than
    1.09
     normal
    1.07
    究竟
    1.06
    Activations Density 0.190%

    No Known Activations