© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2663
    Prev
    Next
    INDEX
    Explanations

    código abierto

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron flags tokens written in other languages or scripts (i.e. non-English/Latin words).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     可以
    0.57
    <0x99>
    0.55
    s
    0.50
     ਦ
    0.50
     모습
    0.49
    nW
    0.48
     能
    0.47
    một
    0.46
    kons
    0.46
     由
    0.46
    POSITIVE LOGITS
     altamente
    0.86
     empresarial
    0.80
     ocult
    0.80
     marít
    0.78
     cliente
    0.77
     informática
    0.77
     circadian
    0.77
     similares
    0.75
     sindical
    0.75
     celular
    0.75
    Activations Density 0.000%

    No Known Activations