© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 69863
    Prev
    Next
    INDEX
    Explanations

    questions starting with "why"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     your
    -1.89
    Your
    -1.18
     yourself
    -1.13
    your
    -1.13
    出错
    -1.01
    <0xDE>
    -0.95
     Ihren
    -0.95
    regardless
    -0.94
     Anbieter
    -0.92
    trying
    -0.91
    POSITIVE LOGITS
     you
    3.03
     might
    1.53
     شما
    1.44
     você
    1.31
     You
    1.20
    You
    1.18
     may
    1.16
     jūs
    1.16
     Might
    1.11
     then
    1.06
    Activations Density 0.027%

    No Known Activations