© 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. 30350
    Prev
    Next
    INDEX
    Explanations

    case numbers and dates

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

    This neuron fires on uppercase table-column labels (like CONTAINER, ID, IMAGE, COMMAND, CREATED, STATUS, PORTS) in command-line tabular output.

    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
    佢
    -0.92
    委员会
    -0.83
    isyon
    -0.76
    Созда
    -0.75
     リ
    -0.75
    ஷ
    -0.72
     lungs
    -0.70
    NTSTATUS
    -0.70
     frase
    -0.69
     Mour
    -0.69
    POSITIVE LOGITS
     גם
    0.77
     jednak
    0.74
     diritto
    0.73
     mwaka
    0.73
     résister
    0.72
    casi
    0.71
    riceps
    0.69
    ޔ
    0.69
     address
    0.69
     стол
    0.69
    Activations Density 0.009%

    No Known Activations