© 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. 24217
    Prev
    Next
    INDEX
    Explanations

    why questions and explanations

    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
     primate
    0.69
     powied
    0.67
    ेश्च
    0.58
     impor
    0.57
    ิค
    0.57
     distin
    0.55
     margarita
    0.55
    钏
    0.55
     Downey
    0.55
     importancia
    0.54
    POSITIVE LOGITS
    ك
    0.67
    เป็น
    0.65
     chỉ
    0.61
    .
    0.60
    ếu
    0.59
    ہ
    0.59
    将
    0.59
    จะ
    0.58
    最
    0.58
    ка
    0.57
    Activations Density 0.082%

    No Known Activations