© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11515
    Prev
    Next
    INDEX
    Explanations

    yoga and yoga school

    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_9_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
    েই
    2.88
    वट
    2.56
    า
    2.56
     embark
    2.55
    ব্য
    2.43
     άλλ
    2.36
    nbsp
    2.35
    ><?
    2.34
     unem
    2.32
     floss
    2.32
    POSITIVE LOGITS
    assertThat
    3.44
     Kegiatan
    2.75
    ни
    2.70
     vä
    2.65
     świecie
    2.65
    뻣
    2.64
    acara
    2.61
    ৩৫
    2.58
     conoc
    2.57
    Ві
    2.55
    Activations Density 0.011%

    No Known Activations