© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111400
    Prev
    Next
    INDEX
    Explanations

    nailing or nails

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

    The neuron fires on occurrences of the “nail” family of words (e.g. nail, nails, nailed, nailing, nailer).

    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
     調整
    -2.41
    borderSide
    -2.34
    didSet
    -2.34
     經典
    -2.31
     และ
    -2.30
    鯓
    -2.19
    梣
    -2.17
    馀
    -2.13
     腕
    -2.11
    The
    -2.09
    POSITIVE LOGITS
     
    2.08
     comienzan
    2.02
    薆
    1.98
     могут
    1.95
     puedan
    1.89
    心の
    1.87
     provocando
    1.87
     colocando
    1.84
     tendrán
    1.82
     realizando
    1.82
    Activations Density 0.005%

    No Known Activations