© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 36196
    Prev
    Next
    INDEX
    Explanations

    negation operator ¬

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     أم
    1.77
    דת
    1.50
    د
    1.49
    ة
    1.48
    𝟬
    1.46
    ่
    1.38
     او
    1.37
    ഓ
    1.37
     أجل
    1.36
     الاجتماعية
    1.33
    POSITIVE LOGITS
    ет
    2.27
    ⿵
    2.11
    на
    2.05
    enschaft
    1.91
     browned
    1.80
    м
    1.72
    っいて
    1.71
     siquiera
    1.70
    ゥム
    1.70
    р
    1.70
    Activations Density 0.000%

    No Known Activations