© 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. 8505
    Prev
    Next
    INDEX
    Explanations

    just practice

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

    This neuron detects the boundaries between text chunks (i.e. paragraph/segment separators).

    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
    n
    0.95
    сибир
    0.87
     DEJ
    0.84
     Defts
    0.84
     silicate
    0.84
    iende
    0.81
     tetrahydro
    0.81
     sieve
    0.81
     delineate
    0.80
     siphon
    0.80
    POSITIVE LOGITS
    <h4>
    0.68
    ர்
    0.67
    Detailed
    0.67
     piu
    0.66
     رفتار
    0.65
     Datensch
    0.64
     полу
    0.64
    ър
    0.63
    ем
    0.63
    хе
    0.63
    Activations Density 0.000%

    No Known Activations