© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25253
    Prev
    Next
    INDEX
    Explanations

    All I want/need/can

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

    This neuron detects self-referential clauses where the writer uses “I” (often followed by a verb) to describe their own actions or experience.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    鹩
    -1.41
    
    -1.38
     抠
    -1.36
     火鍋
    -1.34
    澌
    -1.30
     短发
    -1.30
     花纹
    -1.30
    臜
    -1.27
     guantes
    -1.27
    蟶
    -1.27
    POSITIVE LOGITS
     that
    1.72
     can
    1.62
     I
    1.54
     in
    1.47
     You
    1.46
     is
    1.45
     new
    1.37
     S
    1.35
     for
    1.32
     you
    1.32
    Activations Density 0.028%

    No Known Activations