© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2089
    Prev
    Next
    INDEX
    Explanations

    lists questions about choices

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

    The neuron fires strongly on opening quotation‐mark tokens (i.e. the “ character at the start of quoted segments).

    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
     "
    1.63
     "[
    1.55
     "'
    1.51
     "¿
    1.46
     ("
    1.45
     “
    1.43
     "...
    1.39
     "`
    1.39
     "\
    1.38
     "_
    1.38
    POSITIVE LOGITS
    text
    1.40
    error
    1.40
    super
    1.39
    private
    1.38
    false
    1.37
    new
    1.36
    user
    1.36
    common
    1.36
    padding
    1.35
    value
    1.34
    Activations Density 0.310%

    No Known Activations