© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16003
    Prev
    Next
    INDEX
    Explanations

    cannot and will not

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

    The neuron is strongly triggered by coordinating connectives (e.g. “and,” “nor,” “but,” “or,” and similar linking/negative function words).

    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
     infectious
    0.71
     carcinoma
    0.68
    1
    0.66
    2
    0.65
     menstrual
    0.63
     serviceable
    0.63
     sperm
    0.61
     cycl
    0.61
     कहते
    0.61
     steer
    0.59
    POSITIVE LOGITS
    elabel
    0.70
     IncludeField
    0.66
     thisTrial
    0.66
    RatingDiff
    0.66
    甴
    0.66
    kz
    0.65
    udahkan
    0.65
     Explained
    0.64
     Trained
    0.64
    therners
    0.64
    Activations Density 0.101%

    No Known Activations