© 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. 102841
    Prev
    Next
    INDEX
    Explanations

    Openstack Nova server

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

    The neuron fires on numeric tokens (digits and numbers, e.g. version numbers, sizes, and other numeric literals).

    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
     appartiennent
    -1.00
    rupulous
    -0.91
     tré
    -0.88
    ຂ
    -0.87
     commencent
    -0.86
     musée
    -0.83
    temper
    -0.82
    方には
    -0.82
    another
    -0.82
    ៖
    -0.81
    POSITIVE LOGITS
     payment
    0.85
     amount
    0.85
     destroy
    0.81
     enable
    0.81
     size
    0.80
     client
    0.80
    énération
    0.79
     storage
    0.78
     period
    0.76
    Enzyme
    0.75
    Activations Density 0.007%

    No Known Activations