© 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. 58037
    Prev
    Next
    INDEX
    Explanations

    field reference

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

    The neuron fires strongly on numeric literals (sequences of digits) in code or data.

    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
    USU
    -0.85
    ゞ
    -0.79
     withRouter
    -0.79
     teile
    -0.79
    AlreadyExists
    -0.79
     Morphology
    -0.78
     Timeout
    -0.77
    éton
    -0.76
    Mich
    -0.75
    Grado
    -0.75
    POSITIVE LOGITS
     mandatory
    1.13
     display
    1.10
     required
    1.08
     validation
    1.07
     control
    1.05
     input
    1.03
     lookup
    1.02
     width
    1.00
     search
    0.99
     visible
    0.97
    Activations Density 0.028%

    No Known Activations