© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1806
    Prev
    Next
    INDEX
    Explanations

    3D models and data

    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
    К
    1.44
    Ч
    1.40
    Вы
    1.40
    Что
    1.31
    0
    1.27
    То
    1.23
    Т
    1.22
    Ку
    1.21
    Все
    1.20
    ૦
    1.20
    POSITIVE LOGITS
    oretically
    1.19
    is
    1.18
     virtually
    1.16
     almost
    1.13
    る
    1.12
     subprocess
    1.11
    ে
    1.10
     and
    1.10
     nearly
    1.10
     sev
    1.09
    Activations Density 0.166%

    No Known Activations