© 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. 22-GEMMASCOPE-RES-131K
    7. 66131
    Prev
    Next
    INDEX
    Explanations

    glass and related materials

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

    The neuron detects technical terms referring to laminated glass assemblies (e.g. bent‐laminated windshields and insulated glass panels).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ҍ
    -1.20
     апреля
    -1.15
    ;';
    -1.14
    ங
    -1.13
    DDS
    -1.12
     тү
    -1.10
     oogen
    -1.09
    ковая
    -1.09
     Ahnung
    -1.06
    īg
    -1.05
    POSITIVE LOGITS
     glass
    1.72
    glass
    1.23
    一見
    1.16
     optics
    1.16
    fractive
    1.13
    idikan
    1.12
    fflush
    1.11
     стек
    1.09
     овощи
    1.09
    Keep
    1.08
    Activations Density 0.051%

    No Known Activations