© 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. 34-GEMMASCOPE-RES-131K
    7. 57993
    Prev
    Next
    INDEX
    Explanations

    opt for, everything that

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

    The neuron responds to numeric tokens and their associated measure or list‐style contexts (e.g. digits, years, quantities, and numbered headings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     politica
    -0.80
     deus
    -0.79
    ది
    -0.78
     Där
    -0.77
    Propagation
    -0.76
    Waarom
    -0.76
     mercen
    -0.75
     fini
    -0.75
    Galeria
    -0.74
    GALLERY
    -0.73
    POSITIVE LOGITS
    ised
    0.79
    眯
    0.79
     pliers
    0.78
     crown
    0.75
    |
    0.74
     linked
    0.73
     asegurado
    0.72
     Wolver
    0.72
    |'
    0.70
     ז
    0.69
    Activations Density 0.015%

    No Known Activations