© 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. 29986
    Prev
    Next
    INDEX
    Explanations

    i statements expressing feelings or actions

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

    First person statements about self

    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
     ప్రస్తు
    0.46
     ইঙ্গিত
    0.46
     ఇప్పటికే
    0.45
     అత
    0.44
     శు
    0.44
     addNew
    0.43
     விழுப்புரம்
    0.43
     അവളുടെ
    0.43
    镐
    0.43
     डाउट्स
    0.43
    POSITIVE LOGITS
     strives
    0.46
    grav
    0.45
    servicetime
    0.45
    enjoy
    0.44
     enjoys
    0.44
     enjoyed
    0.43
     enjoy
    0.43
    purs
    0.43
     strive
    0.42
     forty
    0.42
    Activations Density 0.055%

    No Known Activations