© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 7755
    Prev
    Next
    INDEX
    Explanations

    format, instructions, examples

    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_16k_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
    ся
    1.52
    서
    1.51
    h
    1.42
    o
    1.41
    nobyl
    1.34
    ছেন
    1.23
    ис
    1.20
    PickerDialog
    1.18
    vieve
    1.16
    ography
    1.11
    POSITIVE LOGITS
     concaten
    1.27
    অত
    1.27
    وت
    1.20
     PROVID
    1.18
    หรือ
    1.17
    가
    1.16
     বৈশিষ্ট্য
    1.15
     aspects
    1.14
    נט
    1.14
    רה
    1.12
    Activations Density 0.232%

    No Known Activations