© 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. 40-GEMMASCOPE-2-RES-262K
    7. 23708
    Prev
    Next
    INDEX
    Explanations

    plasma, magnetic fields, charged particles

    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_40_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
    培训
    0.48
    税务
    0.48
     налого
    0.47
     ставак
    0.47
     Culinary
    0.46
    诏
    0.46
    财务
    0.45
    膑
    0.45
     crumble
    0.45
    邀请
    0.45
    POSITIVE LOGITS
     plasma
    1.36
     plasmas
    1.27
    Plasma
    1.23
    plasma
    1.22
     Plasma
    1.16
     geomagnetic
    0.96
     ion
    0.95
     magnetic
    0.94
     PLASMA
    0.94
     magnet
    0.89
    Activations Density 0.014%

    No Known Activations