© 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. 39150
    Prev
    Next
    INDEX
    Explanations

    percentages or accuracy

    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
     logarithms
    1.58
    ্যে
    1.47
    ㅠㅠ
    1.44
    യും
    1.43
    هاء
    1.43
     misunderstand
    1.41
    ের
    1.40
    ד
    1.39
    ্রমে
    1.38
     personalise
    1.38
    POSITIVE LOGITS
    isasi
    1.91
    ната
    1.70
    č
    1.54
    ба
    1.46
    ção
    1.44
     anak
    1.43
     artificielle
    1.43
     awal
    1.42
    ada
    1.41
     à
    1.41
    Activations Density 0.001%

    No Known Activations