© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31131
    Prev
    Next
    INDEX
    Explanations

    content followed by punctuation

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

    This neuron detects the plus sign used in timestamp or metadata fields to indicate a timezone offset (e.g. “+2940000”).

    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
    🐜
    -0.88
     would
    -0.84
    🐍
    -0.83
    ︹
    -0.79
    aventura
    -0.78
    )--(
    -0.77
    ياه
    -0.76
     any
    -0.76
    vyšší
    -0.76
     ditambah
    -0.76
    POSITIVE LOGITS
    OWSKI
    0.91
    bilis
    0.91
     dreary
    0.85
    もちゃ
    0.85
     gebildet
    0.82
     streamlining
    0.82
    TRY
    0.81
    owskiego
    0.80
     Herbs
    0.79
     overthrown
    0.79
    Activations Density 0.000%

    No Known Activations