© 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. 22-GEMMASCOPE-RES-131K
    7. 14486
    Prev
    Next
    INDEX
    Explanations

    lists of items or attributes

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

    The main thing this neuron does is detect numeric literals (integers or decimals) in the text.

    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
    ണം
    -0.97
    BOTH
    -0.85
    Eksterne
    -0.77
     ideen
    -0.76
    非常好
    -0.76
     toujours
    -0.76
    ativeness
    -0.74
    틱
    -0.74
    很好
    -0.74
    better
    -0.73
    POSITIVE LOGITS
    tactical
    0.92
    Swish
    0.84
    蔷
    0.83
    locales
    0.79
    Lenny
    0.75
     acknowledging
    0.73
    Pyrene
    0.73
    Tongue
    0.73
     acknowledge
    0.71
    ख्य
    0.71
    Activations Density 0.100%

    No Known Activations