© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99375
    Prev
    Next
    INDEX
    Explanations

    wanna gonna future actions

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

    The neuron flags informal, colloquial “filler” or slang tokens (e.g. wanna, gonna, pra, tô/ta, vai) typical of casual spoken style.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    焄
    -3.02
    珰
    -2.48
    ↑↑↑</
    -2.41
    蛱
    -2.20
     ผ้า
    -2.11
    jaqueta
    -2.09
     ใหญ่
    -2.08
    cherichia
    -2.08
    汭
    -2.08
    嬲
    -2.05
    POSITIVE LOGITS
    𖣘
    2.78
    er
    2.19
    硨
    2.16
     been
    1.94
    Somehow
    1.94
    O
    1.93
     таких
    1.91
    ra
    1.91
     subjug
    1.90
    ba
    1.84
    Activations Density 0.009%

    No Known Activations