© 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. 11052
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles

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

    This neuron spikes only at the very start of each new news‐story segment, effectively marking paragraph/article boundaries rather than any particular words inside them.

    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
     पासवर्ड
    0.63
     contará
    0.62
     hükü
    0.60
     některé
    0.60
     Barcelone
    0.59
     açı
    0.58
     poursuit
    0.57
     అక్క
    0.57
     कर्नाटक
    0.57
     yüzde
    0.57
    POSITIVE LOGITS
    or
    0.60
    /
    0.59
     または
    0.55
    ia
    0.54
    ir
    0.54
    RES
    0.52
    iological
    0.51
     또는
    0.51
     શુભેચ્છાઓ
    0.50
    aceous
    0.50
    Activations Density 0.058%

    No Known Activations