© 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. 25543
    Prev
    Next
    INDEX
    Explanations

    technical terms and actions

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

    The neuron is triggered by numeric tokens—especially numbers and measurements, often with decimals.

    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
     걸
    -0.94
     beyond
    -0.93
    hilt
    -0.86
     among
    -0.82
     between
    -0.82
     against
    -0.82
     ибо
    -0.81
     Parliament
    -0.80
    Wrist
    -0.80
    について
    -0.80
    POSITIVE LOGITS
    ❓
    1.24
    😞
    1.15
    ××
    1.02
    anyway
    1.01
    👍👍
    0.99
    😪
    0.98
    🌟
    0.98
    quartered
    0.97
    ❗
    0.96
    ❗️
    0.96
    Activations Density 0.143%

    No Known Activations