© 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-16K
    7. 7258
    Prev
    Next
    INDEX
    Explanations

    related to medical terms and scientific descriptions

    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
    ون
    1.24
    ال
    1.23
    u
    1.14
    el
    1.09
    us
    1.09
    oretically
    1.09
    ي
    1.09
    й
    1.06
     Ş
    1.05
     promov
    1.05
    POSITIVE LOGITS
     formularios
    1.15
    dihydroxy
    1.11
     kutoka
    1.10
    HOR
    1.09
    textures
    1.06
     pakas
    1.06
    အတူ
    1.05
     Ehm
    1.03
     человеком
    1.03
    Historia
    1.02
    Activations Density 0.001%

    No Known Activations