© 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. 9166
    Prev
    Next
    INDEX
    Explanations

    experienced after

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

    The neuron chiefly responds to function words—especially determiners and possessive pronouns such as “some” and “his.”

    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
    њем
    0.79
    ність
    0.78
    ರುವ
    0.76
    ็อก
    0.75
     wakt
    0.72
    栱
    0.72
    rupción
    0.71
     কয়েকটি
    0.71
    ンプ
    0.69
    ルの
    0.69
    POSITIVE LOGITS
    ет
    0.87
     hyst
    0.84
     ממש
    0.84
     her
    0.82
     ссы
    0.82
     също
    0.80
    -
    0.79
     bamb
    0.79
     foi
    0.77
     byl
    0.77
    Activations Density 0.000%

    No Known Activations