© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1891
    Prev
    Next
    INDEX
    Explanations

    ended up

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

    The neuron strongly activates on verbs—particularly past-tense and participle forms that denote completed or ongoing actions.

    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
    -
    1.19
    :
    0.96
    '
    0.93
    /
    0.88
     atau
    0.78
     quale
    0.76
    !
    0.76
     וש
    0.75
     meth
    0.75
    --
    0.74
    POSITIVE LOGITS
    大量的
    0.88
    ल्लिंग
    0.82
    ल्ज
    0.79
    Quantidade
    0.78
    ные
    0.77
    尿
    0.76
    いっぱい
    0.75
    tsch
    0.74
    ेच्छा
    0.73
     Finances
    0.73
    Activations Density 0.013%

    No Known Activations