© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 119660
    Prev
    Next
    INDEX
    Explanations

    trouble and emotion

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

    Global symbol for romance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    고
    0.59
    アン
    0.55
    childComplexity
    0.54
    ક
    0.52
     Jocelyn
    0.50
    োহণ
    0.49
     Quadrupèdes
    0.49
    まん
    0.49
    ein
    0.49
    сында
    0.48
    POSITIVE LOGITS
    Emotional
    0.53
     emotional
    0.49
     emocional
    0.48
    婆
    0.45
    ם
    0.45
     emotionally
    0.45
     it
    0.44
     term
    0.44
     эмоциона
    0.44
     sanciones
    0.44
    Activations Density 0.001%

    No Known Activations