© 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. 14972
    Prev
    Next
    INDEX
    Explanations

    less in

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

    This neuron responds most strongly to less common, lower‐frequency words (i.e. relatively rare vocabulary items).

    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
    م
    0.87
    simo
    0.75
     圖
    0.75
     конструк
    0.72
     направи
    0.72
     MUM
    0.72
     Recap
    0.72
     из
    0.71
    Дан
    0.70
     KMeans
    0.70
    POSITIVE LOGITS
    er
    0.91
    or
    0.79
    markdown
    0.72
     হয়তো
    0.71
     सब्सक्राइब
    0.70
    ամ
    0.70
    ا
    0.70
    orice
    0.69
    em
    0.68
    environments
    0.67
    Activations Density 0.000%

    No Known Activations