© 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. 1515
    Prev
    Next
    INDEX
    Explanations

    calculator statistics

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

    This neuron fires on mentions of formal document or writing assignments—words like “essay,” “paper,” “business plan,” “research,” “template,” etc., indicating requests or titles for structured written documents.

    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
    0.46
    Ị
    0.42
    :}
    0.39
     Sử
    0.38
    ()
    0.38
    (?)
    0.38
     Missions
    0.37
    }
    0.37
    ั
    0.36
    =>
    0.36
    POSITIVE LOGITS
     bestellen
    0.54
     hvad
    0.52
     tshirt
    0.50
     whats
    0.49
     xray
    0.48
     ipad
    0.47
     hoodies
    0.46
     uk
    0.46
     pdf
    0.46
     achat
    0.46
    Activations Density 0.212%

    No Known Activations