© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70801
    Prev
    Next
    INDEX
    Explanations

    import org

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

    The neuron fires on standalone numeric tokens (literal numbers, e.g. version numbers or other numeric constants).

    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
     weiteres
    -1.00
     Francus
    -0.96
     Peut
    -0.94
     what
    -0.94
     беже
    -0.94
    zera
    -0.93
     kertoo
    -0.93
     clearColor
    -0.89
     فوت
    -0.88
     nunc
    -0.87
    POSITIVE LOGITS
    Tazama
    1.06
    ]>=
    0.95
    Ệ
    0.95
     flechas
    0.93
     CGFloat
    0.92
     särsk
    0.91
     require
    0.90
    実装
    0.88
    Gemeinsame
    0.88
     seperti
    0.88
    Activations Density 0.051%

    No Known Activations