© 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. 117266
    Prev
    Next
    INDEX
    Explanations

    positive sentiment words

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

    The neuron strongly activates on first-person singular pronouns (the word “I”), marking sentences where the author refers to themselves.

    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
     нравится
    -0.87
     segítség
    -0.82
     Ча
    -0.81
     Priority
    -0.81
    を感じる
    -0.79
    ęs
    -0.78
     precedence
    -0.78
     BoxFit
    -0.78
    cjon
    -0.77
     blitt
    -0.76
    POSITIVE LOGITS
     loved
    5.34
    Loved
    4.03
     enjoyed
    4.00
     Loved
    4.00
     liked
    3.91
    loved
    3.78
     LOVED
    3.52
    Enjoyed
    2.52
    liked
    2.47
     adored
    2.34
    Activations Density 0.057%

    No Known Activations