© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 212
    Prev
    Next
    INDEX
    Explanations

    follow the instructions

    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_9_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
    य
    1.83
    요
    1.72
    𝐚
    1.58
    -(\
    1.56
    𝑎
    1.51
     Alltag
    1.49
    說
    1.48
     следующие
    1.48
    மான
    1.43
     keď
    1.43
    POSITIVE LOGITS
    s
    1.71
    oubtedly
    1.64
     afield
    1.57
    ិច
    1.51
     चलकर
    1.50
    alphabet
    1.46
     exhale
    1.46
     Tiếp
    1.46
    friday
    1.45
    ElementSibling
    1.44
    Activations Density 1.821%

    No Known Activations