© 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. 5756
    Prev
    Next
    INDEX
    Explanations

    list item markers

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

    The neuron detects Roman-numeral section or chapter headings.

    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
    _
    1.16
    s
    0.93
    ్య
    0.80
     awali
    0.80
    >
    0.80
    mig
    0.78
    //
    0.78
    iendo
    0.78
    recen
    0.78
    }
    0.78
    POSITIVE LOGITS
     FTSE
    1.04
     GCSE
    0.91
     USDC
    0.90
     exemptions
    0.88
     devotes
    0.87
     appellants
    0.86
     affords
    0.85
     exemption
    0.84
     EMEA
    0.84
     Ту
    0.84
    Activations Density 0.054%

    No Known Activations