© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 3247
    Prev
    Next
    INDEX
    Explanations

    disclaimers

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

    The neuron primarily activates on the em-dash punctuation (the “—” character) marking abrupt breaks or asides.

    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
    ?),
    1.00
    ?).
    0.94
    )$
    0.92
    !!)
    0.82
     варианты
    0.80
     однако
    0.79
     omkring
    0.79
     belangrijke
    0.79
     sidelined
    0.79
     idem
    0.78
    POSITIVE LOGITS
    is
    1.08
    or
    0.95
    a
    0.95
    on
    0.95
    Shortly
    0.92
    namely
    0.92
    та
    0.92
    ar
    0.91
    Every
    0.91
    Regardless
    0.91
    Activations Density 0.032%

    No Known Activations