© 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. 50503
    Prev
    Next
    INDEX
    Explanations

    server versions and software

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

    The neuron fires on numeric version tokens (e.g. “2000,” “2003,” “2008,” etc.) and related software edition identifiers.

    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
    ဗ
    -0.76
    Então
    -0.75
    Today
    -0.74
    BORN
    -0.73
    handling
    -0.73
    闺
    -0.72
    KURZ
    -0.71
    getResult
    -0.71
     zvý
    -0.70
    skyl
    -0.70
    POSITIVE LOGITS
    datasource
    0.76
    sik
    0.69
     occasione
    0.69
    maxX
    0.68
     thighs
    0.68
     Caves
    0.67
     syphilis
    0.67
     Cousin
    0.67
    天然
    0.66
    FileInfo
    0.66
    Activations Density 0.048%

    No Known Activations