© 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. 79180
    Prev
    Next
    INDEX
    Explanations

    information and learning

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

    strategic increase, successful, region of, conversational, import

    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
    Not in Any Lists

    No Comments

    Negative Logits
     parede
    0.53
     parete
    0.52
     produtos
    0.51
    ຸນ
    0.51
     seta
    0.51
    砦
    0.51
     ciertas
    0.50
     productos
    0.49
     paredes
    0.47
    ະພັນ
    0.47
    POSITIVE LOGITS
    Selection
    0.55
    ın
    0.54
    ir
    0.50
    States
    0.49
    Institutional
    0.49
    Kc
    0.48
    ถ
    0.48
    Should
    0.47
    Edition
    0.47
    institutional
    0.47
    Activations Density 0.000%

    No Known Activations