© 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. 33506
    Prev
    Next
    INDEX
    Explanations

    quality of future

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

    The neuron activates on numeral tokens (quantities, measurements, percentages) in the 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
     porción
    -1.12
    letics
    -1.10
     emblem
    -1.09
    HostException
    -1.09
    仅
    -1.06
    ribune
    -1.04
     puis
    -1.02
    .*")]
    -1.00
    では
    -0.99
     arany
    -0.99
    POSITIVE LOGITS
     that
    1.77
     this
    1.25
     warung
    1.12
     面包
    1.01
     bumi
    1.00
    ようですが
    0.98
     открытия
    0.97
    ſam
    0.96
     secondo
    0.96
     souhaitez
    0.94
    Activations Density 0.064%

    No Known Activations