© 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. 11660
    Prev
    Next
    INDEX
    Explanations

    release or publish

    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
    ર
    2.47
     ![](
    2.28
    ように
    2.26
    𝐥
    2.18
    𝐣
    2.17
     Georg
    2.12
     ncol
    2.04
    𝐠
    2.02
     recourse
    1.99
     Rabin
    1.97
    POSITIVE LOGITS
    ant
    2.49
    ियस
    2.41
    asikan
    2.23
    amientos
    2.19
     состоялась
    2.13
    াপ
    2.11
     scare
    2.08
    as
    2.08
    unches
    2.03
    dato
    2.00
    Activations Density 0.110%

    No Known Activations