© 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. 22-GEMMASCOPE-RES-131K
    4. 12960
    Prev
    Next
    INDEX
    Explanations

    Vladimir Putin

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

    The neuron is triggered by numeric tokens—sequences of digits such as version numbers, file identifiers, line numbers, and other standalone numbers in code or filenames.

    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
    ignent
    -0.94
     nº
    -0.93
     heraus
    -0.91
     best
    -0.90
     memoria
    -0.90
    힘
    -0.88
    Dialog
    -0.88
     both
    -0.88
    ESTONE
    -0.88
     número
    -0.87
    POSITIVE LOGITS
     также
    1.23
     télécommande
    1.18
     לאחר
    0.99
     próprios
    0.98
    obrá
    0.95
     fenô
    0.95
     Quien
    0.94
    ственного
    0.91
    semin
    0.91
    also
    0.90
    Activations Density 0.001%

    No Known Activations