© 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. 579
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on blank‐line paragraph breaks (i.e. on standalone newline/empty‐line 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
    ↵↵
    0.75
    ↵↵↵↵
    0.54
    ↵↵↵
    0.52
    ↵↵↵↵↵↵
    0.49
    ↵
    0.48
    ↵↵↵↵↵↵↵↵
    0.48
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.48
    ↵↵↵↵↵
    0.48
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.48
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.48
    POSITIVE LOGITS
     neuronal
    0.44
     यही
    0.42
     superflu
    0.42
     superficially
    0.41
     naquela
    0.41
     émer
    0.40
    <unused226>
    0.40
    quele
    0.39
     instinctively
    0.39
     geographies
    0.39
    Activations Density 0.582%

    No Known Activations