© 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. 5899
    Prev
    Next
    INDEX
    Explanations

    cryptography, logarithm, ket notation

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

    The neuron strongly activates on specialized technical terms and proper nouns (e.g. package or module names, domain-specific jargon).

    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
    '
    0.67
     trotz
    0.59
     tanti
    0.57
     régimen
    0.56
    -
    0.56
    </h2>
    0.55
    at
    0.55
    a
    0.55
     mor
    0.55
     conmigo
    0.55
    POSITIVE LOGITS
    ালী
    0.78
     Allows
    0.78
    ্ের
    0.75
     litres
    0.73
     используются
    0.73
     permet
    0.72
     serums
    0.72
     позволяет
    0.71
     ভাবের
    0.71
    স্থানে
    0.70
    Activations Density 0.001%

    No Known Activations