© 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. 11152
    Prev
    Next
    INDEX
    Explanations

    login frame, train model

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

    The neuron fires on technical or code‐style tokens—things like configuration keys, API parameter names, identifiers, and other jargon you’d see in specs or code rather than ordinary prose.

    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
     నేను
    0.69
     fakat
    0.69
     pewno
    0.66
    µ
    0.66
     vergang
    0.66
     సినిమాలు
    0.65
     ഞാൻ
    0.64
    ?',
    0.64
     powie
    0.63
     जाऊ
    0.63
    POSITIVE LOGITS
    此类
    0.61
     sırasında
    0.57
     unlike
    0.54
     occupant
    0.52
    മാ
    0.52
    ृह
    0.52
     αυτή
    0.51
    ٹین
    0.50
    侧
    0.50
     placeholder
    0.50
    Activations Density 0.193%

    No Known Activations