© 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. 5480
    Prev
    Next
    INDEX
    Explanations

    federal agencies, black spots, kubectl delete, must be

    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
     或者
    1.92
     或
    1.83
     Međutim
    1.78
     ਦੇ
    1.71
     很
    1.70
     nedeni
    1.69
     Regardless
    1.62
     این
    1.62
     但是
    1.61
     ή
    1.57
    POSITIVE LOGITS
    cabinet
    1.66
    btc
    1.58
    eload
    1.56
    platin
    1.53
    <bos>
    1.52
    Читать
    1.49
    protein
    1.48
    oglob
    1.46
    brewer
    1.46
    iPad
    1.42
    Activations Density 0.025%

    No Known Activations