© 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. 26052
    Prev
    Next
    INDEX
    Explanations

    identifiers and code elements

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

    The neuron activates on numeric literal tokens (i.e. sequences of digits) in code.

    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
     vorder
    -1.13
     While
    -1.09
    不可思议
    -1.03
    Omg
    -1.02
     Schwier
    -1.01
     Grunde
    -1.01
     uuidv
    -1.01
    低声
    -1.01
     aforesaid
    -0.99
    collier
    -0.98
    POSITIVE LOGITS
     his
    1.06
     zuvor
    1.02
     guber
    1.01
    贵族
    1.01
    bounded
    1.01
     zoeken
    1.00
     パス
    1.00
     Kün
    0.98
    花的
    0.98
    훙
    0.98
    Activations Density 0.005%

    No Known Activations