© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90488
    Prev
    Next
    INDEX
    Explanations

    section headers or markup

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

    The neuron strongly activates on numeric literals (numbers) 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_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
    <tbody>
    -0.94
    __*/
    -0.90
     Hòa
    -0.89
     even
    -0.88
     claimed
    -0.84
    ahuje
    -0.83
    elding
    -0.81
    乃是
    -0.78
    brar
    -0.77
     legacy
    -0.76
    POSITIVE LOGITS
     propellant
    0.81
    須賀
    0.80
     toutefois
    0.79
     förr
    0.77
    セス
    0.77
     Negative
    0.77
    tachten
    0.77
    凭
    0.77
     غرفة
    0.76
     Goku
    0.76
    Activations Density 0.000%

    No Known Activations