© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90894
    Prev
    Next
    INDEX
    Explanations

    plastic film materials

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

    The neuron is tuned to spot numeric tokens—especially multi‐digit numbers and measurements—throughout the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    frastructure
    -0.82
    expr
    -0.77
    鳴
    -0.76
    IContainer
    -0.75
     RAC
    -0.75
     Bricks
    -0.74
    펩
    -0.72
    粉
    -0.72
    рім
    -0.70
    🏉
    -0.70
    POSITIVE LOGITS
     film
    2.67
     films
    2.44
    film
    2.02
     Film
    1.95
     Films
    1.89
    Film
    1.75
     FILM
    1.70
    Films
    1.65
     sheets
    1.63
    films
    1.63
    Activations Density 0.174%

    No Known Activations