© 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. 16-GEMMASCOPE-2-RES-262K
    7. 28324
    Prev
    Next
    INDEX
    Explanations

    remaining or left over

    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_16_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
    \
    0.77
    は
    0.75
     it
    0.70
    ",
    0.66
     a
    0.65
     genotyping
    0.64
     interruption
    0.64
    :
    0.64
    '
    0.63
     joking
    0.61
    POSITIVE LOGITS
    at
    1.25
     बचे
    1.10
    residual
    1.02
    s
    0.98
    el
    0.93
     অবশিষ্ট
    0.93
    殘
    0.91
    en
    0.91
    remaining
    0.91
     vestiges
    0.90
    Activations Density 0.038%

    No Known Activations