© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10045
    Prev
    Next
    INDEX
    Explanations

    sentence end punctuation

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

    This neuron flags long, continuous multi-sentence passages rather than isolated words or short phrases.

    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_31_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
     “[
    1.33
     “
    1.30
     “(
    1.26
     "
    1.24
     "[
    1.19
    “[
    1.16
     "(
    1.12
     "...
    1.12
     “‘
    1.12
     "¿
    1.11
    POSITIVE LOGITS
    Added
    1.29
    Adds
    0.93
     Added
    0.92
    added
    0.88
    Addition
    0.88
    Adding
    0.88
     added
    0.86
    Indeed
    0.84
    Translation
    0.80
    Cpu
    0.78
    Activations Density 0.073%

    No Known Activations