© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11127
    Prev
    Next
    INDEX
    Explanations

    Feature |

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

    This neuron detects French-language text (notably words with French diacritics).

    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_31_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
     posiblemente
    0.62
    zon
    0.60
     думаю
    0.60
     possíveis
    0.60
    Possibly
    0.60
     seguramente
    0.59
     posibles
    0.59
    絘
    0.58
     رب
    0.55
     যাও
    0.55
    POSITIVE LOGITS
    クロマト
    0.66
     Enough
    0.57
     Saddle
    0.55
    ارہ
    0.54
    etrically
    0.54
     இவ்வாறு
    0.53
     Cielo
    0.53
     beaten
    0.52
    ➜
    0.51
     Elected
    0.51
    Activations Density 0.030%

    No Known Activations