© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201631
    Prev
    Next
    INDEX
    Explanations

    Japanese immigrants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ڑھ
    0.58
    埧
    0.53
    齙
    0.51
    پ
    0.49
     ग्री
    0.47
    మ్‌
    0.47
    ан
    0.47
     cheering
    0.46
     নামাজের
    0.46
    міна
    0.45
    POSITIVE LOGITS
     pres
    0.52
    Pres
    0.47
    pres
    0.47
    Info
    0.45
    _
    0.45
    ués
    0.45
    n
    0.43
     Luz
    0.43
     luz
    0.42
     lightly
    0.42
    Activations Density 0.002%

    No Known Activations