© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146896
    Prev
    Next
    INDEX
    Explanations

    여 / 워 endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     ھ
    0.82
     ch
    0.81
     wild
    0.79
    ⇑
    0.78
     then
    0.78
     अप
    0.78
    चा
    0.78
     contained
    0.77
     ח
    0.76
     y
    0.76
    POSITIVE LOGITS
    리
    1.03
    르
    0.99
    지털
    0.96
    이션
    0.96
    니스
    0.95
    니
    0.91
    리아
    0.91
    기
    0.90
     모양
    0.88
    로운
    0.86
    Activations Density 0.002%

    No Known Activations