© 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. 64713
    Prev
    Next
    INDEX
    Explanations

    study design and results

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

    The neuron detects numeric expressions—counts, measurements, percentages, or statistical values—in scientific 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
    aguer
    -0.88
    rceil
    -0.82
    allage
    -0.81
     amplifier
    -0.81
    conos
    -0.80
     prides
    -0.79
    unl
    -0.79
     rar
    -0.76
    perto
    -0.76
    컸
    -0.75
    POSITIVE LOGITS
     how
    1.16
     accuracy
    0.97
     details
    0.96
     riks
    0.96
     benefits
    0.94
     Meningkatkan
    0.92
     attributes
    0.88
     characteristics
    0.87
    ータス
    0.87
     questions
    0.86
    Activations Density 0.191%

    No Known Activations