© 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. 34-GEMMASCOPE-RES-131K
    7. 58063
    Prev
    Next
    INDEX
    Explanations

    describing characters and stories

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

    This neuron activates on the main review text (the body content of a review) and not on titles, headers, or metadata.

    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
    ߋ
    -1.06
     razonable
    -0.93
    戏剧
    -0.91
    かは
    -0.90
    payer
    -0.87
     uttry
    -0.86
     bumble
    -0.86
    łą
    -0.86
     Stras
    -0.86
     gider
    -0.86
    POSITIVE LOGITS
     readers
    1.41
     characters
    1.10
     reader
    1.09
     sereia
    1.05
    Readers
    1.04
     personnages
    1.04
     inhabiting
    1.02
     protagonist
    1.01
     olvas
    1.00
    characters
    0.99
    Activations Density 0.029%

    No Known Activations