© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15857
    Prev
    Next
    INDEX
    Explanations

    wants free

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

    This neuron fires on content-rich, detail-bearing tokens—especially numbers, proper names, and emphatic or requirement-type words that convey key factual information.

    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_31_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
    ipelago
    0.36
    цы
    0.35
     酒
    0.35
    ები
    0.34
    雨
    0.34
    ㇂
    0.34
    tips
    0.33
    キャッシュ
    0.33
    愉
    0.33
    酒
    0.33
    POSITIVE LOGITS
    こちらも
    0.37
     ebenfalls
    0.36
     akadem
    0.34
     Tensorflow
    0.33
    !!!!!
    0.32
     yine
    0.32
     এখানকার
    0.31
     আবারো
    0.30
     Fannie
    0.30
    これも
    0.30
    Activations Density 0.257%

    No Known Activations