© 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. 117786
    Prev
    Next
    INDEX
    Explanations

    underground utility services

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

    The neuron strongly fires on occurrences of the trademark “Ditch Witch” (and its associated industrial‐equipment terminology and numeric identifiers).

    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
    nější
    -0.87
    baut
    -0.80
    ('');
    -0.75
    Linked
    -0.74
    ၂
    -0.73
    ành
    -0.71
     autofocus
    -0.71
     glabrous
    -0.71
     Demet
    -0.71
    ([]);
    -0.71
    POSITIVE LOGITS
     utility
    1.62
     utilities
    1.59
     underground
    1.44
     Utility
    1.33
    Underground
    1.32
    Utility
    1.31
     Underground
    1.31
    utility
    1.28
     Utilities
    1.24
    Utilities
    1.13
    Activations Density 0.011%

    No Known Activations