© 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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 9539
    Prev
    Next
    INDEX
    Explanations

    body image and language

    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_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
    न
    2.60
    ional
    2.48
    unlike
    2.40
    ibility
    2.34
    ции
    2.32
    ️
    2.32
    ن
    2.30
    ,]
    2.29
     bộ
    2.24
    ية
    2.23
    POSITIVE LOGITS
    то
    2.62
     SafeArea
    2.59
    guards
    2.57
     phận
    2.56
    txtName
    2.35
    д
    2.33
     захо
    2.31
    一丝
    2.29
    yyyyyyyy
    2.27
    WEBPACK
    2.24
    Activations Density 0.084%

    No Known Activations