© 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. 79844
    Prev
    Next
    INDEX
    Explanations

    planning and scheduling

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

    The main thing this neuron does is detect numeric tokens (numbers, including integers and decimals) 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
    amable
    -0.93
    tivate
    -0.92
    TERS
    -0.91
    𝘯
    -0.89
    丰富
    -0.88
    Convenient
    -0.87
    atzes
    -0.87
    Curious
    -0.85
    "}";
    -0.85
     ВО
    -0.84
    POSITIVE LOGITS
     algorithm
    1.34
     decisions
    1.31
     solutions
    1.13
     allocation
    1.13
     decision
    1.08
     planning
    1.08
     calculation
    1.07
     solution
    1.07
     calculations
    1.05
     strategic
    1.04
    Activations Density 0.119%

    No Known Activations