© 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-65K
    7. 4397
    Prev
    Next
    INDEX
    Explanations

    parameters and probability distributions

    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_65k_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
    勇气
    0.52
    抨
    0.52
    🅐
    0.51
     недалеко
    0.50
     إضافة
    0.50
     счастли
    0.49
    াহারের
    0.49
    ববার
    0.48
    <unused2049>
    0.48
    चानक
    0.48
    POSITIVE LOGITS
    _{
    0.66
    -\
    0.63
     \
    0.61
    }{
    0.60
    _{\
    0.60
    _
    0.56
    \
    0.54
    R
    0.53
     perturbation
    0.52
    ^{
    0.52
    Activations Density 0.009%

    No Known Activations