© 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. 103735
    Prev
    Next
    INDEX
    Explanations

    fastening devices and components

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

    The neuron detects mentions of fastening hardware (e.g. fasteners, fastening devices, fastening elements).

    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
    {
    -2.42
    [
    -2.39
     diki
    -2.28
    💖
    -2.25
    (
    -2.22
     Teknik
    -2.20
    🌟
    -2.19
     initWithFrame
    -2.14
    💜
    -2.14
    -^
    -2.09
    POSITIVE LOGITS
    ↵
    2.39
     generalmente
    2.28
     района
    2.27
     können
    2.25
     quizás
    2.22
     bustling
    2.13
     cluttered
    2.11
     sprawling
    2.08
     сдела
    2.05
     tendrás
    2.05
    Activations Density 0.007%

    No Known Activations