© 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. 27893
    Prev
    Next
    INDEX
    Explanations

    programming keywords

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

    The neuron picks up standalone numeric tokens (literal numbers) in code or config texts.

    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
    ził
    -1.11
    廈
    -0.99
     DialogResult
    -0.99
    ｀
    -0.95
    物の
    -0.95
     使っ
    -0.94
    grandchildren
    -0.93
     their
    -0.93
     отредакти
    -0.93
    CheckBreak
    -0.92
    POSITIVE LOGITS
    tedrale
    1.10
    してから
    1.06
     slowest
    1.03
     roadways
    1.01
    Răsp
    0.99
     多少
    0.98
    Siamo
    0.96
     |
    0.93
     einander
    0.93
    设置为
    0.93
    Activations Density 0.001%

    No Known Activations