© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8423
    Prev
    Next
    INDEX
    Explanations

    programming conditional statements

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

    The neuron responds strongest to unusually long, multi‐syllable tokens (i.e. lengthy rare 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
    an
    0.90
    ii
    0.83
    ive
    0.78
    ’
    0.77
     Hotels
    0.76
    3
    0.75
    j
    0.75
    Kh
    0.74
    1
    0.73
    apple
    0.72
    POSITIVE LOGITS
     jurisdict
    0.84
     patric
    0.82
     decret
    0.76
    ଐ
    0.76
     пород
    0.75
     saddo
    0.75
    வர்களாக
    0.75
     discern
    0.74
    ेच्छा
    0.74
     instill
    0.74
    Activations Density 0.003%

    No Known Activations