© 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. 15650
    Prev
    Next
    INDEX
    Explanations

    job details and qualifications

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

    The neuron is keyed to bibliographic‐ or reference‐style lines—i.e. individual citation/section‐header entries.

    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
    er
    0.81
    Kom
    0.80
    ing
    0.79
    r
    0.79
    ى
    0.78
    and
    0.77
    it
    0.75
    ർ
    0.75
    anje
    0.73
    您
    0.70
    POSITIVE LOGITS
     hydrazine
    0.99
     नॉर्म
    0.84
     perspectivas
    0.84
     teapot
    0.81
     gering
    0.80
     explicação
    0.79
     lesiones
    0.77
     biops
    0.76
     lepid
    0.76
     normas
    0.76
    Activations Density 0.001%

    No Known Activations