© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15413
    Prev
    Next
    INDEX
    Explanations

    lions and cats

    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
     불구하고
    1.37
    +}\
    1.21
    +},
    1.20
    то
    1.17
    +}(
    1.15
     nächste
    1.15
     человеком
    1.08
    біль
    1.08
    ᆨ
    1.07
    ଵ
    1.07
    POSITIVE LOGITS
    ম
    1.20
    y
    1.19
    nip
    1.18
    ようになって
    1.18
    proficiency
    1.12
    恪
    1.10
    girl
    1.08
    multiply
    1.08
    निय
    1.07
    +#+#
    1.06
    Activations Density 0.050%

    No Known Activations