© 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-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 72
    Prev
    Next
    INDEX
    Explanations

    square root of negative one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    al
    0.93
    el
    0.93
    is
    0.89
    i
    0.88
     and
    0.85
    бот
    0.85
    on
    0.84
    don
    0.83
    are
    0.80
    ed
    0.79
    POSITIVE LOGITS
     espaces
    1.11
     variétés
    1.00
     collège
    1.00
    푦
    1.00
     itinéraires
    0.99
     fillColorSpace
    0.98
     ϒ
    0.96
     nėra
    0.93
    𝐽
    0.91
     millas
    0.91
    Activations Density 0.000%

    No Known Activations