© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 116195
    Prev
    Next
    INDEX
    Explanations

    soar and increase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     mesmos
    0.57
     pcMove
    0.56
    Defocused
    0.54
     HUOBI
    0.54
     }{}_{\
    0.54
    एसआय
    0.52
    いた
    0.51
    っこ
    0.51
     disintegrated
    0.50
    ஹ
    0.50
    POSITIVE LOGITS
    la
    0.61
    t
    0.57
    ongs
    0.46
     مم
    0.46
     Funding
    0.45
    inderella
    0.44
     Standards
    0.44
    ärke
    0.43
     Call
    0.42
     الأساس
    0.42
    Activations Density 0.000%

    No Known Activations