© 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. 1978
    Prev
    Next
    INDEX
    Explanations

    business, social impact, economics

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

    The neuron is strongly activated by numeric tokens representing decimal‐point values (floating‐point numbers).

    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
     vài
    0.66
     옷
    0.58
     thậm
    0.57
     mặc
    0.55
    ార్లు
    0.53
     vẫn
    0.53
    anız
    0.52
     cramps
    0.52
     몇
    0.52
    WORKDIR
    0.52
    POSITIVE LOGITS
     empowerment
    0.91
     sustainability
    0.79
     societal
    0.79
     stewardship
    0.75
     innovation
    0.75
     sostenibilidad
    0.75
     empowers
    0.74
     inclusivity
    0.74
     experiential
    0.73
     philanthropy
    0.73
    Activations Density 0.414%

    No Known Activations