© 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. 34-GEMMASCOPE-RES-131K
    7. 91672
    Prev
    Next
    INDEX
    Explanations

    books, albums, novels

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

    The neuron detects numeric tokens—its activation grows with the size of the number.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     merve
    -1.13
     citazioni
    -1.08
     csal
    -1.01
     تريد
    -1.00
     boissons
    -0.98
     esqueleto
    -0.95
     astuces
    -0.94
     tromper
    -0.94
     exemplos
    -0.94
     remarque
    -0.93
    POSITIVE LOGITS
     the
    0.99
    ))$.
    0.96
     Dafür
    0.94
     μὲν
    0.90
     sarcas
    0.90
     La
    0.90
    Ѕ
    0.89
     svn
    0.88
     annulus
    0.88
     Когда
    0.86
    Activations Density 0.036%

    No Known Activations