© 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. 10-GEMMASCOPE-RES-131K
    7. 43886
    Prev
    Next
    INDEX
    Explanations

    CPU, processor, hardware components

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

    This neuron selectively activates on numeric tokens—numbers, version digits, and measurements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    unków
    -1.58
    ität
    -1.48
    「
    -1.45
     \"
    -1.35
     Atención
    -1.33
    了一个
    -1.32
    釤
    -1.30
    玧
    -1.29
     associées
    -1.27
     DevComponents
    -1.27
    POSITIVE LOGITS
    Ｗ
    1.41
     being
    1.33
    <td>
    1.32
     maneuver
    1.27
    Приготовление
    1.26
     been
    1.17
     are
    1.16
    0
    1.16
     examined
    1.16
     think
    1.16
    Activations Density 0.014%

    No Known Activations