© 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. 24-GEMMASCOPE-2-RES-16K
    7. 13961
    Prev
    Next
    INDEX
    Explanations

    multi-lingual vocabulary

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

    This neuron detects blank‐or‐masked spans and parenthesized foreign/annotated segments (e.g. sequences of underscores and tokens inside parentheses).

    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
     Calculate
    0.73
     x
    0.72
     calculates
    0.71
     caliper
    0.70
     diameter
    0.69
     calcular
    0.66
     Calcular
    0.66
     also
    0.65
     osnov
    0.65
     Prandtl
    0.65
    POSITIVE LOGITS
    Vocabulary
    0.96
     зарубе
    0.88
    词
    0.85
     vocab
    0.84
    inguém
    0.84
    留学
    0.84
     Vocabulary
    0.83
    句子
    0.83
     употреб
    0.82
    句
    0.81
    Activations Density 0.008%

    No Known Activations