© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83404
    Prev
    Next
    INDEX
    Explanations

    foreign language or segmented words

    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
     prescription
    0.48
    Government
    0.47
     consecutive
    0.45
     Prescription
    0.44
    毕竟
    0.44
     zwią
    0.44
    老人
    0.42
    ؛
    0.42
     بخ
    0.41
     reservation
    0.40
    POSITIVE LOGITS
     ditu
    0.48
    ́c
    0.46
    phdr
    0.45
    itió
    0.45
    etur
    0.44
    pedido
    0.43
    illas
    0.43
    رير
    0.43
    叼
    0.43
    қта
    0.42
    Activations Density 0.004%

    No Known Activations