© 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. 123907
    Prev
    Next
    INDEX
    Explanations

    questions about email, school, and people's ages

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

    after concepts or events

    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
     permettre
    0.52
     résoudre
    0.49
     risolvere
    0.48
     conséquences
    0.48
     succes
    0.47
     telefono
    0.45
    鱼
    0.45
     menyebabkan
    0.44
     आयोग
    0.44
     possibilità
    0.44
    POSITIVE LOGITS
     전시
    0.42
    agi
    0.39
    型
    0.39
    vní
    0.39
     사람
    0.38
     ehemal
    0.38
     antiguos
    0.38
    jumping
    0.38
    ®,
    0.38
     تأثير
    0.38
    Activations Density 0.002%

    No Known Activations