© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7072
    Prev
    Next
    INDEX
    Explanations

    flexibility and flexbox

    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_22_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
    liness
    1.15
    χος
    0.95
    ۥ
    0.94
    ാവ്
    0.91
     تقری
    0.90
    ائلة
    0.89
    极其
    0.89
    鹧
    0.89
    نوان
    0.89
    летний
    0.88
    POSITIVE LOGITS
    ibilität
    1.31
    ures
    1.16
    ibilité
    1.14
     tiden
    1.08
    ibilities
    1.07
     accommodate
    1.04
    ibility
    1.03
    ured
    1.03
     manoeuvre
    1.03
    itime
    0.97
    Activations Density 0.087%

    No Known Activations