© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73043
    Prev
    Next
    INDEX
    Explanations

    specific entity beginnings

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

    The neuron fires on standalone numeric tokens (sequences of digits), i.e. it flags numbers.

    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
    前から
    -0.90
    ależ
    -0.90
    وب
    -0.88
     Males
    -0.82
     musli
    -0.82
     gik
    -0.81
     palo
    -0.79
     reciproc
    -0.79
     dager
    -0.79
    РЭ
    -0.78
    POSITIVE LOGITS
     Añade
    0.96
     "`
    0.96
    ې
    0.94
     tylko
    0.91
    Enough
    0.90
     llevaron
    0.90
    一方で
    0.89
     enough
    0.86
    ่านั้น
    0.86
     pohy
    0.85
    Activations Density 0.001%

    No Known Activations