© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 30445
    Prev
    Next
    INDEX
    Explanations

    numbers and units like kg or %

    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
     approximating
    0.44
    amp
    0.44
    류
    0.41
    cx
    0.39
    s
    0.39
    tene
    0.39
    かう
    0.39
    to
    0.38
    bj
    0.38
     approximations
    0.38
    POSITIVE LOGITS
     kiz
    0.52
    民间
    0.47
     Senator
    0.46
     inFile
    0.46
    苏
    0.46
    lardı
    0.46
     Kiz
    0.45
     Viator
    0.44
     Архів
    0.44
     Susie
    0.44
    Activations Density 0.036%

    No Known Activations