© 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. 82499
    Prev
    Next
    INDEX
    Explanations

    photo ID or CV

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

    The neuron fires on content‐bearing capitalized and technical keywords (e.g. proper nouns, product or document names, and other salient terms).

    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
     jette
    -0.82
     الرس
    -0.77
     Whist
    -0.76
     precedes
    -0.76
    ifter
    -0.75
    Graphic
    -0.74
    graphic
    -0.73
     boite
    -0.73
    bana
    -0.73
    zów
    -0.73
    POSITIVE LOGITS
     photo
    1.74
     photograph
    1.46
     photos
    1.45
     Photo
    1.45
     recent
    1.35
    Photo
    1.30
    照片
    1.26
    PHOTO
    1.24
    photo
    1.22
     portrait
    1.16
    Activations Density 0.010%

    No Known Activations