© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2277
    Prev
    Next
    INDEX
    Explanations

    very followed by a descriptor

    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
    я
    3.09
    <0xA6>
    2.91
    ्य
    2.79
    ේ
    2.53
    rinsim
    2.52
     Macquarie
    2.51
    با
    2.50
    й
    2.48
    ղ
    2.44
     jen
    2.43
    POSITIVE LOGITS
    ق
    2.79
    thing
    2.48
    ник
    2.43
    س
    2.43
    此
    2.43
    𝚑
    2.42
    ج
    2.40
    дцать
    2.39
    time
    2.39
    tze
    2.34
    Activations Density 0.258%

    No Known Activations