© 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. 27660
    Prev
    Next
    INDEX
    Explanations

    NetVista, tokyo, La

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

    The neuron detects numeric tokens (digits or number-like strings) 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
    ができます
    -1.02
    ごめん
    -0.96
     många
    -0.96
    Emit
    -0.91
     duduk
    -0.90
    Hence
    -0.89
    ümüş
    -0.88
     szár
    -0.88
    hender
    -0.87
    secu
    -0.86
    POSITIVE LOGITS
    了一会儿
    0.94
     aanbod
    0.90
    Эзоҳ
    0.90
    erat
    0.88
     expects
    0.86
     asfalto
    0.85
    chige
    0.85
    ありますが
    0.83
    MARC
    0.81
     here
    0.81
    Activations Density 0.025%

    No Known Activations