© 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. 64698
    Prev
    Next
    INDEX
    Explanations

    software versions

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

    This neuron detects numeric software version strings (e.g. “1.2.3”, “==2.0.1”, “>=3.4.5”).

    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
     IndexError
    -1.15
    usahaan
    -0.96
    weile
    -0.93
    ∑
    -0.92
    wirt
    -0.92
     querem
    -0.91
    pergillus
    -0.91
    ,:),
    -0.91
    ,:]
    -0.90
     lære
    -0.90
    POSITIVE LOGITS
    즘
    0.99
     теперь
    0.94
    ꯆ
    0.94
    ionine
    0.93
    actylus
    0.92
     now
    0.89
    лна
    0.89
     Beide
    0.89
     fraudul
    0.89
     monopol
    0.88
    Activations Density 0.038%

    No Known Activations