© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79666
    Prev
    Next
    INDEX
    Explanations

    topics, dates, and labels

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

    The neuron fires on numeric tokens—especially standalone numbers or numeric measurements (including floats and integers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    läs
    -1.16
     refusé
    -1.09
    ()}
    -1.06
     žem
    -1.05
    andafter
    -1.03
    Wszyst
    -1.00
    本日
    -1.00
    梅雨
    -0.98
     rencontré
    -0.98
    我们
    -0.98
    POSITIVE LOGITS
    no
    1.15
     no
    1.13
    ha
    0.96
    ut
    0.94
    ho
    0.92
    看不到
    0.92
    外部連結
    0.92
    </em>
    0.90
    ja
    0.90
    ,
    0.89
    Activations Density 0.008%

    No Known Activations