© 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. 7161
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and code snippets

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

    The neuron activates on standalone numeric literals (sequences of digits).

    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
    XXXXXX
    -0.83
     remains
    -0.79
     领
    -0.78
     beiden
    -0.75
    silent
    -0.75
     Wege
    -0.74
    ganya
    -0.73
    remains
    -0.73
    ntax
    -0.70
    𝐸
    -0.70
    POSITIVE LOGITS
    üf
    0.94
    ................
    0.85
    SqlDataReader
    0.82
     прово
    0.80
                                   
    0.77
    illerato
    0.77
     déf
    0.76
     equit
    0.75
    !』
    0.75
    AAAAAAAAAAAAAAAA
    0.75
    Activations Density 0.020%

    No Known Activations