© 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-262K
    7. 12186
    Prev
    Next
    INDEX
    Explanations

    Extracting, importing, orchestrating, injecting actions

    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_262k_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
     tưởng
    0.59
     завжди
    0.54
    atians
    0.53
    <unused1040>
    0.52
     отлича
    0.52
    <unused115>
    0.52
    ayvachi
    0.52
     ಆಗ
    0.51
     Having
    0.51
    <unused246>
    0.51
    POSITIVE LOGITS
    izes
    1.24
     می‌کند
    1.15
    рует
    1.14
    uje
    1.11
    ifies
    1.09
    합니다
    1.09
    вает
    1.05
    한다
    1.04
     takes
    1.04
    izuje
    1.04
    Activations Density 0.141%

    No Known Activations