© 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. 112483
    Prev
    Next
    INDEX
    Explanations

    love, hate, and wants

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

    The neuron fires on words and phrases expressing personal preference, positive judgment, or enjoyment.

    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
    ,
    -1.15
    .
    -0.98
    の場合は
    -0.97
    isatie
    -0.96
    viel
    -0.95
     was
    -0.95
    лія
    -0.93
    我們
    -0.93
     الصيف
    -0.92
     قوله
    -0.92
    POSITIVE LOGITS
     it
    1.60
     its
    1.55
     It
    1.29
    因为它
    1.23
     jsou
    1.20
     protože
    1.20
    Also
    1.18
     also
    1.16
    也能
    1.16
     оно
    1.16
    Activations Density 0.134%

    No Known Activations