© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90078
    Prev
    Next
    INDEX
    Explanations

    film debut

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

    The neuron selectively lights up on capitalized named entities—proper names, movie titles, and other title‐case or all‐caps tokens.

    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
    imantan
    -0.80
    ////
    -0.76
    ontology
    -0.75
    toBe
    -0.74
    acionais
    -0.73
    damente
    -0.72
     Forex
    -0.71
     発送
    -0.69
    гра
    -0.69
    路線
    -0.68
    POSITIVE LOGITS
    stark
    0.81
    眸
    0.80
     Shah
    0.78
     Mega
    0.76
    balloon
    0.76
    Clique
    0.75
     تناول
    0.74
    idste
    0.74
    mög
    0.73
     hudeb
    0.71
    Activations Density 0.009%

    No Known Activations