© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8932
    Prev
    Next
    INDEX
    Explanations

    negotiation and agreement terms

    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
    躍
    1.09
     stocking
    0.96
     calories
    0.96
     eclectic
    0.93
     rejuven
    0.92
     s
    0.91
     bohemian
    0.91
    ’
    0.89
     inhal
    0.89
     audits
    0.89
    POSITIVE LOGITS
     agreements
    1.35
    ي
    1.25
     ताकि
    1.23
     agreement
    1.23
    Agreement
    1.20
     anlaş
    1.20
    LE
    1.18
    gabe
    1.16
    agreement
    1.16
     согла
    1.15
    Activations Density 0.099%

    No Known Activations