© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26120
    Prev
    Next
    INDEX
    Explanations

    mathematical 'for', 'at', 'to'

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

    The neuron is primarily detecting and activating on numerical tokens (i.e. numbers) 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
     We
    -1.28
     AND
    -1.22
     -
    -1.20
     And
    -1.20
     You
    -1.18
    𝟏
    -1.15
     nuestra
    -1.10
    os
    -1.10
     problem
    -1.09
     for
    -1.08
    POSITIVE LOGITS
     gyere
    1.24
    `,
    
    1.21
     odo
    1.18
    ("");
    
    1.16
    اژ
    1.14
    . 
    1.13
     美丽
    1.13
     stabil
    1.13
    也将
    1.12
     fiatal
    1.12
    Activations Density 0.004%

    No Known Activations