© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59140
    Prev
    Next
    INDEX
    Explanations

    wave and waving

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

    The neuron is primarily detecting personal pronouns (like “I,” “me,” “he”) that mark a narrative viewpoint.

    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
     Retrofit
    -0.76
     Condem
    -0.74
     Vö
    -0.71
    //*[@
    -0.70
    Horst
    -0.69
     Statements
    -0.69
    fwd
    -0.69
    pA
    -0.68
     TBA
    -0.67
     Maher
    -0.67
    POSITIVE LOGITS
     waved
    4.84
     waving
    4.53
     wave
    4.47
    wave
    3.70
     Wave
    3.69
    Wave
    3.53
     waves
    3.31
    WAVE
    3.05
     WAVE
    2.94
    waves
    2.75
    Activations Density 0.021%

    No Known Activations