© 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. 23067
    Prev
    Next
    INDEX
    Explanations

    years and political figures

    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
    🫶
    1.38
    🥹
    1.36
    🥲
    1.28
    🤍
    1.25
    🫠
    1.19
    🩷
    1.14
    🫣
    1.13
    🫂
    1.13
    🫐
    1.13
    🥸
    1.12
    POSITIVE LOGITS
     ২০১৭
    1.42
     ২০১৮
    1.41
     Brexit
    1.16
     Trump
    1.09
    Brexit
    1.08
    Trump
    1.05
    🖒
    1.02
     ২০১৯
    0.91
     millennials
    0.85
     ट्रंप
    0.81
    Activations Density 0.028%

    No Known Activations