© 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. 14076
    Prev
    Next
    INDEX
    Explanations

    opening sequences and details

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

    This neuron fires on words that introduce or signal narrative structure or section headings (e.g. “tale,” “book,” “opens,” “Plot,” “chapter”), marking story beginnings or transitions.

    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
     who
    -1.77
    {
    -1.67
     from
    -1.46
     in
    -1.28
    XXIII
    -1.27
    0
    -1.26
     viewWillAppear
    -1.24
     Erschein
    -1.23
    ).
    -1.22
     însă
    -1.21
    POSITIVE LOGITS
    ⤹
    1.48
     an
    1.47
     tatuagem
    1.44
     langage
    1.38
     verbess
    1.38
     chaine
    1.38
     musée
    1.37
     toalha
    1.34
    ть
    1.31
     femenino
    1.30
    Activations Density 0.036%

    No Known Activations