© 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. 4986
    Prev
    Next
    INDEX
    Explanations

    ASCII characters and code structure

    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
    ३
    1.62
    Cadastro
    1.54
    étation
    1.51
     রকমের
    1.41
    pN
    1.41
    १
    1.39
    ४
    1.39
    commonByteArray
    1.39
    Paradise
    1.38
    ৩
    1.38
    POSITIVE LOGITS
     acesta
    1.37
     moist
    1.29
     endemic
    1.26
     expense
    1.16
     resulting
    1.15
     obsession
    1.14
     aceasta
    1.11
     rotten
    1.11
     im
    1.10
     sober
    1.08
    Activations Density 0.163%

    No Known Activations