© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33818
    Prev
    Next
    INDEX
    Explanations

    java, oracle, and android development

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

    The neuron primarily detects numeric tokens (digits and version numbers) in the 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
     mollus
    -0.74
    Capricorn
    -0.73
     Kant
    -0.72
    gotta
    -0.71
     empfind
    -0.70
    ATRO
    -0.69
     bool
    -0.68
    achat
    -0.67
    לע
    -0.66
     reduziert
    -0.66
    POSITIVE LOGITS
     java
    1.61
    java
    1.47
     javax
    1.28
     SUN
    1.20
    javax
    1.08
    SUN
    0.98
     sun
    0.98
    classes
    0.95
     Sun
    0.93
    Ljava
    0.93
    Activations Density 0.097%

    No Known Activations