© 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. 11413
    Prev
    Next
    INDEX
    Explanations

    lists starting with '

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

    This neuron is highly sensitive to the very first content token immediately following a chunk start, effectively marking the beginning of each new text segment.

    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
    ar
    0.68
    0.66
    eff
    0.66
     JFrame
    0.65
    Os
    0.63
    et
    0.61
    am
    0.61
    <unused60>
    0.61
     tops
    0.61
    ড়ের
    0.61
    POSITIVE LOGITS
    ENSITY
    0.92
    रात
    0.91
    维生素
    0.91
     большая
    0.89
    하시는
    0.87
     губерна
    0.86
     Большая
    0.85
    nagar
    0.85
     cuarta
    0.85
     толькі
    0.85
    Activations Density 0.001%

    No Known Activations