© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27414
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

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

    The neuron is specialized for spotting numeric sequences (multi‐digit tokens) such as the ID numbers embedded in image‐file or page‐scan references.

    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
     vya
    -1.16
     COLUMBIA
    -1.08
     trimestre
    -1.05
     pistolet
    -1.04
     maso
    -1.02
    OGLE
    -1.02
     velg
    -1.02
     Tél
    -1.01
     consectetur
    -1.01
     csapat
    -1.01
    POSITIVE LOGITS
     etc
    1.09
    8
    1.09
     et
    1.07
    があり
    1.06
     algunas
    1.06
     algunos
    1.03
    这就
    1.03
    6
    1.03
    0
    1.02
    5
    1.02
    Activations Density 0.008%

    No Known Activations