© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2112
    Prev
    Next
    INDEX
    Explanations

    do you questions

    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_17_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
    en
    1.81
    te
    1.75
     ∂
    1.70
    त
    1.63
    tio
    1.62
    $\$
    1.59
     доля
    1.59
    ly
    1.58
    ر
    1.57
     able
    1.56
    POSITIVE LOGITS
    к
    2.12
    omsday
    1.90
    鵑
    1.85
    ငန်း
    1.85
     складу
    1.71
    entes
    1.68
    鹃
    1.64
     Согласно
    1.60
    helial
    1.59
     fehlen
    1.58
    Activations Density 0.220%

    No Known Activations