© 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. 6869
    Prev
    Next
    INDEX
    Explanations

    scope, block, module

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

    This neuron picks out code‐style or technical tokens—things like command‐line flags, programming keywords, punctuation/symbol sequences, and version or numeric identifiers.

    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
     વ
    0.60
    .])
    0.59
     விர
    0.58
     स्पे
    0.57
     বাংলায়
    0.55
     அதி
    0.54
    ೆಂದು
    0.54
     防水
    0.54
    )+'
    0.54
     [])
    0.54
    POSITIVE LOGITS
     Chud
    0.56
     Chuck
    0.55
     constituencies
    0.54
     leads
    0.54
    Chuck
    0.53
     leadership
    0.52
     bial
    0.51
     excepciones
    0.51
    kov
    0.50
     mult
    0.49
    Activations Density 0.001%

    No Known Activations