© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128676
    Prev
    Next
    INDEX
    Explanations

    The neuron is strongly triggered by text describing thoroughbred horse racing (race names, horses, distances, and results).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    planning to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیگران
    -1.09
     kapag
    -1.07
     cristianismo
    -1.05
     balcón
    -1.03
     pamoja
    -1.01
    futbolista
    -1.01
     kuhusu
    -1.01
     part
    -0.99
    埼
    -0.97
    取り付け
    -0.96
    POSITIVE LOGITS
     десер
    1.08
    amerikanischer
    1.07
    льевич
    1.04
    embolso
    1.01
    OwnerId
    0.98
     merawat
    0.97
     veran
    0.96
     her
    0.96
    Terror
    0.95
    </tbody>
    0.93
    Activations Density 0.035%

    No Known Activations