© 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. 24382
    Prev
    Next
    INDEX
    Explanations

    publicly available

    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
     Warranty
    0.30
    可能有
    0.30
     nếu
    0.29
     Qualquer
    0.29
     якщо
    0.29
     ако
    0.28
    くなります
    0.28
    咣
    0.28
    اگر
    0.28
     নাগরিক
    0.28
    POSITIVE LOGITS
    three
    0.36
     zarówno
    0.33
    intervention
    0.32
     intervene
    0.32
     sowohl
    0.31
    two
    0.31
     personas
    0.30
     benthic
    0.30
    sey
    0.30
    ሁ
    0.29
    Activations Density 0.093%

    No Known Activations