© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70322
    Prev
    Next
    INDEX
    Explanations

    names and dates

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

    The neuron activates on numeric tokens (sequences of digits), such as years and other 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_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
     sätta
    -1.01
     äta
    -0.98
     börja
    -0.94
     köpa
    -0.94
     lägga
    -0.94
     hjälpa
    -0.92
     tänka
    -0.85
     habitación
    -0.84
    Predecesor
    -0.84
     daban
    -0.84
    POSITIVE LOGITS
    eqnarray
    1.13
    ppa
    1.11
    tta
    1.08
     IgA
    1.05
    rolla
    1.02
    rgba
    0.98
    gca
    0.98
    ísima
    0.98
    ndra
    0.97
    RGBA
    0.96
    Activations Density 0.063%

    No Known Activations