© 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. 5862
    Prev
    Next
    INDEX
    Explanations

    fossil fuels

    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
    т
    2.17
    י
    2.17
    ا
    2.09
    ي
    2.06
    al
    2.02
    ла
    1.96
    こちらの
    1.95
    ר
    1.93
    któ
    1.91
    ع
    1.90
    POSITIVE LOGITS
    stocks
    1.78
    橥
    1.53
    relationships
    1.52
     Pardon
    1.52
    age
    1.48
    hands
    1.47
    titanic
    1.47
    것
    1.47
    }>
    1.46
    aceous
    1.46
    Activations Density 0.001%

    No Known Activations