© 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. 10-GEMMASCOPE-RES-131K
    7. 21575
    Prev
    Next
    INDEX
    Explanations

    bulk

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

    The neuron consistently fires on occurrences of the word “bulk” (including its variants or substrings), regardless of context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵
    -2.98
     verbess
    -2.17
     Then
    -2.13
     erforder
    -2.08
    铪
    -1.95
     внутрен
    -1.93
     generando
    -1.82
     consequence
    -1.77
     glimpses
    -1.77
     Incidentally
    -1.77
    POSITIVE LOGITS
     bagus
    2.44
    bulk
    2.23
    𓆜
    2.13
    橚
    2.09
     atau
    2.08
    䉴
    2.05
    釓
    2.05
     Bulk
    2.00
    埙
    1.98
    亊
    1.95
    Activations Density 0.010%

    No Known Activations