© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 92914
    Prev
    Next
    INDEX
    Explanations

    and one or two

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

    The neuron selectively activates on numeric tokens (i.e., isolated 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
     vagyok
    -1.10
     kabát
    -0.99
     logiciels
    -0.96
    给大家
    -0.94
     sostu
    -0.92
     einstellen
    -0.92
     tiroirs
    -0.91
     Utilisez
    -0.89
    缓解
    -0.87
     commentaires
    -0.86
    POSITIVE LOGITS
     also
    1.09
     &
    1.03
    <()>
    0.97
    land
    0.94
    oriya
    0.93
     dalamnya
    0.92
    3
    0.90
    creens
    0.89
     stata
    0.88
     tersebut
    0.88
    Activations Density 0.059%

    No Known Activations