© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7018
    Prev
    Next
    INDEX
    Explanations

    but introducing contrast or 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_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
     bzw
    0.24
     arba
    0.22
     ಹಾಗೂ
    0.21
     IconButton
    0.21
    を中心
    0.20
    り
    0.20
     vormen
    0.19
     ayudan
    0.19
     `/
    0.19
     beurre
    0.19
    POSITIVE LOGITS
     not
    0.34
    not
    0.29
     doesn
    0.28
     ikke
    0.28
     cannot
    0.28
    ไม่ใช่
    0.27
     lacks
    0.26
    不是
    0.26
     όχι
    0.26
     не
    0.25
    Activations Density 0.619%

    No Known Activations