© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72087
    Prev
    Next
    INDEX
    Explanations

    epoxy, nose, microsomal, copyright, effect

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

    technical or chemical terms, particularly those related to compounds or materials.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on concrete industrial or infrastructure terms—specific materials or structural components (e.g. “Screed,” “Epoxy,” “aerobridge,” “lines”).

    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
     focuses
    -1.37
     suspensão
    -1.35
    尨
    -1.30
     глю
    -1.23
    だけです
    -1.21
     lesiones
    -1.20
     gravidez
    -1.19
     Eſ
    -1.18
    すっ
    -1.18
     Início
    -1.17
    POSITIVE LOGITS
     any
    1.80
     during
    1.76
     should
    1.45
     or
    1.43
     with
    1.37
     on
    1.34
     насеља
    1.30
    зык
    1.30
     shall
    1.28
    ');
    
    1.27
    Activations Density 0.000%

    No Known Activations