© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25375
    Prev
    Next
    INDEX
    Explanations

    explains why something is available or accessible

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

    The neuron primarily activates on numeric tokens or quantitative expressions (e.g. digits, percentages, and decimal‐number tokens).

    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
    จะ
    -0.98
     your
    -0.90
     should
    -0.88
    izin
    -0.87
    édition
    -0.86
    ឹ
    -0.85
     כבר
    -0.84
     already
    -0.83
    Already
    -0.83
     posisi
    -0.83
    POSITIVE LOGITS
     incentives
    1.33
     incentive
    1.21
     available
    1.08
     availability
    1.01
    Incenti
    0.95
     accessible
    0.91
     доступ
    0.91
     it
    0.90
     disponib
    0.90
     accessibility
    0.90
    Activations Density 0.085%

    No Known Activations