© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11091
    Prev
    Next
    INDEX
    Explanations

    responsibilities

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

    The neuron fires strongly on low‐frequency, content‐bearing tokens (i.e. uncommon or “information‐rich” words).

    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
    ل
    1.02
    ва
    0.93
    ні
    0.92
    م
    0.90
    ка
    0.89
    म
    0.88
    лого
    0.86
    दार
    0.84
    м
    0.84
    و
    0.84
    POSITIVE LOGITS
     mengakses
    0.78
     aérea
    0.73
     assistance
    0.73
     ambitions
    0.73
     humility
    0.72
    னவே
    0.71
    ahan
    0.70
     spy
    0.70
     lainnya
    0.70
     instill
    0.70
    Activations Density 0.000%

    No Known Activations