© 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. 13387
    Prev
    Next
    INDEX
    Explanations

    This neuron fires strongly on relatively rare, content-bearing words (especially proper nouns and technical terms) rather than common 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_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
     is
    0.98
     S
    0.96
     has
    0.91
     D
    0.89
     are
    0.87
     have
    0.87
     G
    0.86
     B
    0.84
     can
    0.84
     marijuana
    0.84
    POSITIVE LOGITS
    During
    1.00
    Throughout
    0.95
     һәм
    0.93
     במהלך
    0.93
    Während
    0.86
    during
    0.86
    Although
    0.84
    1
    0.84
     және
    0.83
    Durante
    0.83
    Activations Density 0.000%

    No Known Activations