© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9200
    Prev
    Next
    INDEX
    Explanations

    `panels`, `vectors`, `floating` | `q`, `be`, `guarantees`, `directly`, `ence`, `can`, `-` | `satisfe`, `soddisf`, `ahanglan`, `pourra`, `diligent`, `धानिक`, `necesariamente`, `рни`, `toujours`, `idem`mixed language technical terms

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

    The neuron fires strongly on phrases that require or mention providing a hyperlink back to an original source (e.g. “link back to…”).

    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
    .
    0.80
    |
    0.76
    :
    0.73
    a
    0.71
    '
    0.70
    落在
    0.68
    *
    0.67
    !
    0.66
     กล
    0.66
    ？
    0.66
    POSITIVE LOGITS
     satisfe
    0.86
     soddisf
    0.80
     possibilità
    0.75
    ahanglan
    0.73
    仅仅
    0.72
     necesariamente
    0.71
     pourra
    0.70
    であるが
    0.70
     possibilidade
    0.69
     sondern
    0.68
    Activations Density 0.003%

    No Known Activations