© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5326
    Prev
    Next
    INDEX
    Explanations

    numbers, code, and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    તના
    0.58
     preventable
    0.58
     γνωσ
    0.58
     Mission
    0.57
     kann
    0.57
     refurbished
    0.57
     disgr
    0.56
    ㈤
    0.56
    Descrição
    0.56
    venidos
    0.55
    POSITIVE LOGITS
    ührt
    0.55
     avanzar
    0.54
     partire
    0.53
    𝘨
    0.53
     uygulama
    0.52
     depo
    0.52
    nya
    0.50
     odre
    0.50
    itett
    0.50
     lalu
    0.48
    Activations Density 0.089%

    No Known Activations