© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128634
    Prev
    Next
    INDEX
    Explanations

    specific terms and structures

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    สห
    0.55
    жан
    0.54
    ጐ
    0.52
     sahiptir
    0.51
    スタンダ
    0.50
     inverso
    0.49
    ンの
    0.49
    股份有限公司
    0.49
    ﻜ
    0.47
    ຈະ
    0.46
    POSITIVE LOGITS
    ott
    0.51
    iv
    0.49
     defaults
    0.47
     ott
    0.46
    0.46
     implants
    0.44
    ui
    0.44
    oomla
    0.43
     Hamm
    0.43
     Genetic
    0.43
    Activations Density 0.001%

    No Known Activations