© 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. 34-GEMMASCOPE-RES-131K
    7. 116135
    Prev
    Next
    INDEX
    Explanations

    hemoglobin, in vitro

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

    programming language-related code, particularly focusing on R programming syntax and documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron mainly detects numeric tokens and version‐style number sequences (e.g. software version numbers) in code or technical 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
    [[
    -0.76
     [[
    -0.74
    Processor
    -0.74
    list
    -0.71
     small
    -0.71
     tet
    -0.69
     list
    -0.69
    Blow
    -0.68
     Pres
    -0.68
     la
    -0.67
    POSITIVE LOGITS
    cran
    1.00
     package
    0.98
     CR
    0.91
     Depends
    0.90
    Vig
    0.89
    CR
    0.89
    ffè
    0.87
     pkg
    0.84
    vig
    0.83
    Depends
    0.83
    Activations Density 0.144%

    No Known Activations