© 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. 3054
    Prev
    Next
    INDEX
    Explanations

    operations and roles

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

    The neuron strongly activates on infrequent, out-of-vocabulary or proper-noun tokens (e.g. rare names, UI labels like “comments”/“pings,” unusual words), i.e. it’s detecting uncommon or unexpected tokens.

    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
    CH
    0.79
    함
    0.78
    ਰ
    0.77
    
    0.76
    element
    0.75
    ાડ
    0.72
    вил
    0.72
     положение
    0.71
     incidente
    0.71
    전
    0.71
    POSITIVE LOGITS
     itertools
    0.90
     mindless
    0.86
     Honestly
    0.83
     Assuming
    0.82
     assuming
    0.82
     Suppose
    0.82
     unspo
    0.82
     Mosul
    0.80
     cuál
    0.79
     চেয়ে
    0.79
    Activations Density 0.000%

    No Known Activations