© 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. 10-GEMMASCOPE-RES-131K
    7. 71282
    Prev
    Next
    INDEX
    Explanations

    movie and book titles

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

    The neuron responds to capitalized proper names—especially film titles, character names, and other named entities—in 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_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
     люблю
    -1.26
    jó
    -1.23
    fak
    -1.20
    θλη
    -1.20
     摄影
    -1.20
    mik
    -1.19
     वै
    -1.19
     cielos
    -1.13
    itatis
    -1.13
    posite
    -1.12
    POSITIVE LOGITS
    オススメです
    1.29
     表紙
    1.18
    出来る
    1.17
     by
    1.16
     required
    1.13
     about
    1.12
    LANTA
    1.09
     utilizz
    1.09
     Our
    1.06
    おすすめです
    1.05
    Activations Density 0.030%

    No Known Activations