© 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. 34-GEMMASCOPE-RES-131K
    7. 31333
    Prev
    Next
    INDEX
    Explanations

    full

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

    The neuron is primarily triggered by named entities and section‐level titles—proper nouns like school or movie names, product or project names, license headers, metadata keys, and other headings.

    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
     Zur
    -0.82
     ajudá
    -0.80
    stals
    -0.78
    undaki
    -0.77
     per
    -0.76
    Ĵ
    -0.76
     iulie
    -0.75
     вд
    -0.75
    право
    -0.73
     nueva
    -0.70
    POSITIVE LOGITS
    Full
    1.05
     Full
    1.02
    isFull
    0.99
     Fuller
    0.94
    getFull
    0.91
     FULL
    0.90
     Beds
    0.88
     fuller
    0.87
     toti
    0.84
     ******
    0.82
    Activations Density 0.049%

    No Known Activations