© 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. 73301
    Prev
    Next
    INDEX
    Explanations

    start of code block

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

    The neuron activates on numeric tokens (digits or numbers) in code or queries.

    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
     camisas
    -1.10
    bership
    -1.10
     this
    -1.09
     tagit
    -1.06
     visitas
    -1.02
    出来ない
    -1.02
     municipalité
    -1.01
     garganta
    -0.97
     retirada
    -0.97
     that
    -0.96
    POSITIVE LOGITS
     angepasst
    1.11
    嚟
    1.09
     самом
    1.02
     zwanzig
    1.01
    Uf
    0.98
     همچنین
    0.94
     to
    0.93
    嗌
    0.92
     digitalen
    0.92
    rn
    0.91
    Activations Density 0.006%

    No Known Activations