© 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. 201141
    Prev
    Next
    INDEX
    Explanations

    transitions before phrases

    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
     명이
    0.50
     orthogonal
    0.48
     помимо
    0.45
     ভালোভাবে
    0.44
    ີ່
    0.44
    CCIÓN
    0.44
    氅
    0.43
     ಕಂಡ
    0.43
    టర్‌
    0.42
     Proyecto
    0.41
    POSITIVE LOGITS
    man
    0.46
    বাহ
    0.45
    ford
    0.44
     éprou
    0.43
     нала
    0.43
    ก
    0.42
    (&
    0.42
     administrativas
    0.42
     allerlei
    0.42
    light
    0.41
    Activations Density 0.007%

    No Known Activations