© 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. 65833
    Prev
    Next
    INDEX
    Explanations

    version numbers

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

    The neuron fires on numeric characters appearing in software version strings (e.g. the digits in “1.4.8”, “5.5.0”, “2.4.3.6”, etc.).

    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
     said
    -1.03
    P
    -0.96
     habiendo
    -0.93
    G
    -0.93
    шня
    -0.91
     próprio
    -0.88
    R
    -0.87
    H
    -0.87
     człon
    -0.85
    D
    -0.85
    POSITIVE LOGITS
    Kepala
    1.04
     goma
    1.04
    Informasi
    1.02
    ‌تر
    0.99
     VEH
    0.99
     neige
    0.98
    Lihat
    0.98
     psz
    0.98
     Eſ
    0.97
     chì
    0.96
    Activations Density 0.065%

    No Known Activations