© 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. 10-GEMMASCOPE-RES-131K
    7. 13628
    Prev
    Next
    INDEX
    Explanations

    version numbers

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

    This neuron identifies numeric components of version strings (i.e. the digits in “major.minor.patch” fields).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ’
    -1.64
    vaný
    -1.40
     an
    -1.40
     saith
    -1.38
     salvación
    -1.37
    ету
    -1.37
    XD
    -1.36
    ЛЮ
    -1.35
    (;
    -1.34
     einst
    -1.34
    POSITIVE LOGITS
    <bos>
    2.36
    หรือ
    1.73
     etmeye
    1.62
     tarefas
    1.61
    jenige
    1.59
     onları
    1.55
     conocen
    1.54
    lossians
    1.52
     Reſ
    1.51
     eccellente
    1.50
    Activations Density 0.041%

    No Known Activations