© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100138
    Prev
    Next
    INDEX
    Explanations

    physical openings, apertures, ports

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

    the word "opening" in technical or mechanical contexts, particularly when describing apertures, holes, or access points in devices and structures.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects words referring to physical openings (e.g. “opening,” “hole,” “port,” “aperture”) in a document.

    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
    3
    -1.36
    M
    -1.34
     segurando
    -1.29
    riebene
    -1.28
    _
    -1.21
     drifted
    -1.17
     onderdeel
    -1.16
     fortfarande
    -1.11
    ，“
    -1.09
    enfant
    -1.09
    POSITIVE LOGITS
     BOTH
    1.40
    ropractor
    1.38
     mädchen
    1.35
    produzione
    1.34
     THEOREM
    1.33
    鹟
    1.33
    orrhage
    1.33
    钽
    1.31
    鸪
    1.31
     sesama
    1.31
    Activations Density 0.092%

    No Known Activations