© 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. 12714
    Prev
    Next
    INDEX
    Explanations

    hair ties

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

    The neuron is strongly activated by relatively rare, content‐bearing tokens (e.g. uncommon nouns, verbs in –ing, numbers, adverbs) rather than by 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_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
    Ess
    0.77
    叶
    0.75
    SC
    0.74
    гі
    0.74
    레
    0.74
    Border
    0.73
    Ві
    0.73
    ش
    0.73
    Education
    0.73
    на
    0.72
    POSITIVE LOGITS
     Golpe
    0.88
     synced
    0.86
     sostuvo
    0.84
     dejo
    0.84
     referencias
    0.82
     zyg
    0.82
     Robo
    0.80
     fundamento
    0.80
     legible
    0.79
     cambiar
    0.78
    Activations Density 0.000%

    No Known Activations