© 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. 10-GEMMASCOPE-RES-131K
    7. 73780
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    The neuron activates on numeric tokens and number expressions (both digits and spelled‐out 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_10/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
     it
    -1.42
     there
    -1.36
     comprendere
    -1.35
     guardare
    -1.33
    nému
    -1.31
     circumstance
    -1.30
     see
    -1.30
    ))$_
    -1.28
     crescere
    -1.27
     einzigen
    -1.27
    POSITIVE LOGITS
    𝟏
    1.67
     και
    1.55
     и
    1.51
     và
    1.48
     של
    1.42
     other
    1.38
     ו
    1.37
    InputElement
    1.34
     PyTuple
    1.33
    谴
    1.31
    Activations Density 0.020%

    No Known Activations