© 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. 8833
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to content-bearing, relatively uncommon words (nouns or verbs) rather than high-frequency function words.

    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
    seem
    0.85
    да
    0.84
     собственных
    0.84
    inguém
    0.83
    ming
    0.82
     нрав
    0.82
    ном
    0.80
    ן
    0.80
    mensaje
    0.79
     судь
    0.79
    POSITIVE LOGITS
     heights
    0.70
     alley
    0.68
     Regione
    0.68
     deterior
    0.67
     Tropical
    0.67
     corridors
    0.66
     alleys
    0.63
     nonché
    0.63
     centres
    0.62
     Sulph
    0.62
    Activations Density 0.000%

    No Known Activations