© 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. 102627
    Prev
    Next
    INDEX
    Explanations

    titles of books and films

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

    This neuron detects mentions of published works—titles of books, articles, films, etc., often with leading “The,” colons, or author names.

    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
     by
    -1.57
    赑
    -1.40
     who
    -1.39
     hecha
    -1.34
     its
    -1.34
     it
    -1.34
     gantung
    -1.29
    賑
    -1.29
     fueran
    -1.28
    bcrypt
    -1.27
    POSITIVE LOGITS
     används
    1.19
    jaja
    1.16
     mögliche
    1.05
     菇
    1.05
    bleiben
    1.05
     humeur
    1.05
     spannende
    1.04
     掛け
    1.03
     of
    1.03
    Which
    1.02
    Activations Density 0.082%

    No Known Activations