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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 30276
    Prev
    Next
    INDEX
    Explanations

    discussion of controversy

    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
    1.25
    ش
    1.05
    ן
    1.05
     at
    1.01
    ı
    0.95
     to
    0.95
     on
    0.93
    ш
    0.90
     that
    0.89
    ravel
    0.89
    POSITIVE LOGITS
    К
    1.41
    (
    1.34
     Controversy
    1.23
    ای
    1.13
    Ли
    1.13
     polémica
    1.11
     controversial
    1.10
     controversy
    1.09
    us
    1.09
     Controvers
    1.09
    Activations Density 0.005%

    No Known Activations