© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37956
    Prev
    Next
    INDEX
    Explanations

    drill bit

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

    The neuron strongly activates on mentions of “drill” and related drilling-equipment terms (e.g., drill bit, drilling).

    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
    を務
    -0.90
    vét
    -0.86
    点此
    -0.85
     але
    -0.85
     Fortunately
    -0.84
     zumindest
    -0.83
     Luckily
    -0.83
     rinnov
    -0.83
    Недо
    -0.83
    SBATCH
    -0.83
    POSITIVE LOGITS
     sergeant
    1.21
     Sargent
    0.97
    Sergeant
    0.94
     sar
    0.93
     Serge
    0.92
    𝗢
    0.91
     Sergeant
    0.91
     lloc
    0.88
    master
    0.86
    Serge
    0.84
    Activations Density 0.013%

    No Known Activations