© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3222
    Prev
    Next
    INDEX
    Explanations

    listing examples and more

    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_29_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
    ))&&(
    0.80
    ហើយ
    0.79
     samtidig
    0.78
     ciò
    0.76
    析
    0.75
    <unused2149>
    0.73
    ciò
    0.70
    çoivent
    0.69
    Tro
    0.69
    จํา
    0.69
    POSITIVE LOGITS
     etc
    2.29
     وغيرها
    2.12
    などが
    2.12
    等
    2.04
    など
    2.03
    などは
    2.01
     등이
    1.98
     등의
    1.96
    etc
    1.93
    などの
    1.92
    Activations Density 0.281%

    No Known Activations