© 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. 16-GEMMASCOPE-2-RES-262K
    7. 116941
    Prev
    Next
    INDEX
    Explanations

    emphasizes negation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     It
    0.92
    あります
    0.83
    🖉
    0.81
    無い
    0.80
    꽤
    0.80
    ﻫ
    0.80
    ⬯
    0.78
    িতে
    0.76
    中で
    0.76
    ется
    0.75
    POSITIVE LOGITS
    an
    1.04
    '
    1.00
    p
    1.00
    la
    0.95
     (
    0.94
    rick
    0.93
    cı
    0.93
     whatsoever
    0.91
    on
    0.90
    LEY
    0.89
    Activations Density 0.000%

    No Known Activations