© 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. 10-GEMMASCOPE-RES-131K
    4. 80732
    Prev
    Next
    INDEX
    Explanations

    fasteners and hardware components

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

    The neuron strongly activates on terms naming threaded fastening hardware or tools (e.g. nut, bolt, wrench).

    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
    chtend
    -1.49
     hana
    -1.48
     rois
    -1.45
     Tunes
    -1.45
     hoi
    -1.44
     eſſ
    -1.44
     coa
    -1.37
    nis
    -1.37
     Competence
    -1.35
    菒
    -1.33
    POSITIVE LOGITS
     of
    2.16
    </b>
    1.63
     by
    1.63
     our
    1.62
     if
    1.51
     go
    1.50
     see
    1.44
    </i>
    1.43
     This
    1.43
    </h5>
    1.38
    Activations Density 0.015%

    No Known Activations