© 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. 83127
    Prev
    Next
    INDEX
    Explanations

    unscrew and screw

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

    This neuron fires on numeric specifications and measurements (e.g. dimensions, part numbers, or technical values).

    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
    INCREF
    -0.77
     fries
    -0.74
    Window
    -0.73
    puter
    -0.70
    DIVISION
    -0.69
    ldb
    -0.69
     robbers
    -0.67
     Brind
    -0.66
    ídas
    -0.66
    anned
    -0.65
    POSITIVE LOGITS
     uns
    3.14
     screw
    2.72
     screwing
    2.39
     Screw
    2.34
    Screw
    2.31
     screwed
    2.27
    screw
    2.17
    uns
    1.99
    Uns
    1.96
     Uns
    1.95
    Activations Density 0.042%

    No Known Activations