© 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. 16081
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements

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

    This neuron activates on numeric tokens (integers, decimals, and signed numbers).

    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
     fré
    -0.81
    ત્
    -0.79
     ragione
    -0.76
     zake
    -0.76
    տ
    -0.76
     eki
    -0.75
     klassi
    -0.75
    hdc
    -0.75
     dekoratif
    -0.74
     windshield
    -0.73
    POSITIVE LOGITS
     vertical
    0.83
    線が
    0.79
     height
    0.78
     пак
    0.77
     Sessions
    0.76
     também
    0.76
    CGFloat
    0.76
    坳
    0.75
     temporal
    0.75
     verwenden
    0.75
    Activations Density 0.054%

    No Known Activations