© 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. 78543
    Prev
    Next
    INDEX
    Explanations

    software updates

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

    This neuron fires on numeric codes and version‐style number sequences (e.g., error codes or software version numbers).

    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
     Palin
    -0.83
    賠
    -0.77
     jit
    -0.73
    csr
    -0.72
     llantas
    -0.71
    FD
    -0.70
     relaciones
    -0.69
     recession
    -0.68
    ட்
    -0.68
    jung
    -0.68
    POSITIVE LOGITS
     Update
    1.02
    Updates
    1.00
     Updates
    0.94
     patching
    0.93
     Automatic
    0.90
     WS
    0.90
     updates
    0.89
    Update
    0.89
    Patch
    0.86
     update
    0.83
    Activations Density 0.037%

    No Known Activations