© 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. 13396
    Prev
    Next
    INDEX
    Explanations

    base

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

    The neuron activates on mentions of “UFC” (i.e. references to UFC events or the UFC organization).

    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
     sneaking
    0.75
    Expr
    0.71
     objets
    0.70
     vehicle
    0.68
    И
    0.68
     больших
    0.67
    Numeric
    0.66
     বিয়ের
    0.66
     реша
    0.66
     ##
    0.64
    POSITIVE LOGITS
     holde
    0.82
     necessario
    0.80
    亽
    0.80
    uu
    0.77
    ᅱ
    0.77
    ant
    0.75
    があるので
    0.75
     necessaria
    0.74
     thảo
    0.74
    おそらく
    0.74
    Activations Density 0.002%

    No Known Activations