© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14468
    Prev
    Next
    INDEX
    Explanations

    aiming to win or succeed

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

    The neuron flags references to numbers, statistics, scores or quantitative figures in the text.

    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
     wciąż
    -1.30
     prawie
    -1.16
     evermore
    -1.09
    𝗬
    -1.08
     mutfak
    -1.08
    Öl
    -1.07
     remarkably
    -1.07
    לים
    -1.05
    álního
    -1.05
     intertw
    -1.05
    POSITIVE LOGITS
     win
    1.37
     this
    1.32
     if
    1.16
     success
    1.07
     succeed
    1.02
    陞
    1.00
     get
    0.95
     not
    0.94
     achieve
    0.93
     getting
    0.91
    Activations Density 0.036%

    No Known Activations