© 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. 45286
    Prev
    Next
    INDEX
    Explanations

    specialized terms begin

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

    The neuron fires on the asterisk markers (the “*” at line starts) in license‐header comment blocks.

    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
    HasColumn
    -0.98
     Parigi
    -0.96
     suci
    -0.94
    physical
    -0.94
    şen
    -0.93
     stile
    -0.92
     vœux
    -0.91
     furia
    -0.91
     inkluder
    -0.91
     fysis
    -0.91
    POSITIVE LOGITS
    addContainerGap
    1.41
     and
    1.05
    Rema
    0.94
    )
    0.85
     Expedition
    0.84
     universal
    0.77
    ホット
    0.73
     ign
    0.73
     Always
    0.72
     Home
    0.72
    Activations Density 0.000%

    No Known Activations