© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10212
    Prev
    Next
    INDEX
    Explanations

    track hashtag usage

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

    This neuron fires on promotional, call-to-action language—especially ads selling “tickets.”

    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_31_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
     मैथमेटिक्स
    0.85
     curvatures
    0.84
     geometri
    0.84
    ༘
    0.84
     geometrically
    0.81
     polysaccharides
    0.80
     slidesToShow
    0.80
     बाजू
    0.80
     ventilators
    0.79
    PLEMENT
    0.78
    POSITIVE LOGITS
     B
    0.81
    ei
    0.78
    aa
    0.73
     e
    0.71
    L
    0.71
    ii
    0.71
     T
    0.70
    e
    0.69
     U
    0.69
    tag
    0.69
    Activations Density 0.000%

    No Known Activations