© 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. 147
    Prev
    Next
    INDEX
    Explanations

    red brick

    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
    hero
    2.21
    ^{*
    2.19
    ional
    2.16
    threatening
    2.12
    (\
    2.00
    -\
    1.98
    istage
    1.94
    ỷ
    1.90
    het
    1.81
    Verizon
    1.81
    POSITIVE LOGITS
    色的
    2.87
     haired
    2.23
     brillante
    2.21
    깔
    2.08
    地方
    1.99
    م
    1.92
    稞
    1.92
     اللون
    1.91
    빛
    1.91
     hues
    1.89
    Activations Density 2.371%

    No Known Activations