© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105074
    Prev
    Next
    INDEX
    Explanations

    saw, jigsaw, chain

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

    The neuron is detecting mentions of tools or handheld implements (e.g. flashlight, jigsaw, chainsaw).

    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
     kado
    -1.70
    terrasse
    -1.67
     vinaigre
    -1.65
    由於
    -1.63
     teknis
    -1.52
    pergillus
    -1.52
    komme
    -1.52
    источник
    -1.49
    ञ
    -1.45
    обзор
    -1.41
    POSITIVE LOGITS
    6
    1.71
    1
    1.56
    8
    1.55
    5
    1.48
     various
    1.48
     specified
    1.42
     newfound
    1.41
     either
    1.40
     specially
    1.39
     or
    1.38
    Activations Density 0.087%

    No Known Activations