© 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. 38871
    Prev
    Next
    INDEX
    Explanations

    data fields or structured lists

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

    The neuron detects numeric tokens (individual numbers or multi‐digit sequences).

    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
     how
    -0.99
    NameInMap
    -0.92
    と思いますが
    -0.88
    langsung
    -0.85
     called
    -0.83
    ttää
    -0.82
    prat
    -0.80
    Production
    -0.80
     Production
    -0.79
     transparencia
    -0.79
    POSITIVE LOGITS
    1.06
    0.97
    Debido
    0.96
    0.93
    0.92
    CardBody
    0.91
    0.90
    羔
    0.89
     твер
    0.89
                         
    0.88
    Activations Density 0.126%

    No Known Activations