© 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. 10-GEMMASCOPE-RES-131K
    7. 87048
    Prev
    Next
    INDEX
    Explanations

    names of franchises and titles

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

    The neuron fires on named entities—especially titles of films, books, shows, or other proper-noun media references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     such
    -1.68
     számára
    -1.36
     található
    -1.34
     változ
    -1.30
    ть
    -1.27
    a
    -1.20
     mellett
    -1.18
     kialak
    -1.18
    \\
    -1.17
     olmak
    -1.17
    POSITIVE LOGITS
     to
    1.98
     luxo
    1.38
    餿
    1.30
    〜〜
    1.28
    ーーー
    1.27
     fale
    1.27
    WORLD
    1.21
     spiritu
    1.21
     keď
    1.20
     behulp
    1.19
    Activations Density 0.004%

    No Known Activations