© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12145
    Prev
    Next
    INDEX
    Explanations

    " is " \*

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

    This neuron fires on the first substantive token that appears immediately after an opening quotation mark.

    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
     หลังจาก
    0.91
    .;
    0.84
     );
    0.82
     ;
    0.80
     นอกจาก
    0.75
     .)
    0.75
    !;
    0.74
    ;
    0.74
     ;,
    0.73
     เพราะ
    0.73
    POSITIVE LOGITS
    oretically
    1.13
    ”（
    0.82
    」
    0.78
    〟
    0.76
    」(
    0.74
    」（
    0.72
    ной
    0.72
    𝗰
    0.72
    〞
    0.67
    」、
    0.67
    Activations Density 0.184%

    No Known Activations