© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73891
    Prev
    Next
    INDEX
    Explanations

    previously

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

    The neuron activates on tokens representing numeric values (e.g., years, measurements, or 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_10/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
     for
    -2.50
     by
    -2.03
    ),
    -1.99
     after
    -1.98
     from
    -1.96
     To
    -1.81
     starts
    -1.73
     at
    -1.67
    </h2>
    -1.65
     with
    -1.63
    POSITIVE LOGITS
    鹇
    2.22
    ⸂
    1.92
    mbgg
    1.91
    蕖
    1.88
    previously
    1.88
    鲧
    1.87
     ་
    1.80
     dando
    1.80
     toalha
    1.73
    ਗ਼
    1.73
    Activations Density 0.058%

    No Known Activations