© 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. 2691
    Prev
    Next
    INDEX
    Explanations

    list markers and emphasis

    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
    (
    1.81
    es
    1.79
    )
    1.52
    '
    1.50
    en
    1.43
    _
    1.43
    "
    1.42
    i
    1.29
    \
    1.26
    ي
    1.25
    POSITIVE LOGITS
     financiero
    1.31
     libertarian
    1.26
    <unused2130>
    1.23
    と呼ばれる
    1.21
     ambito
    1.20
     Möglichkeit
    1.19
    ‌.
    1.16
     unassuming
    1.16
     necessário
    1.16
     empresarial
    1.15
    Activations Density 0.310%

    No Known Activations