© 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. 10-GEMMASCOPE-RES-131K
    7. 3860
    Prev
    Next
    INDEX
    Explanations

    attenuates hyper or amp

    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_10/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
     and
    -2.72
    0
    -2.61
    路的
    -2.08
    ۸
    -2.03
    atellite
    -2.03
    eclamp
    -2.02
    工作的
    -1.96
    试图
    -1.91
    省市镇
    -1.90
    }}$
    -1.88
    POSITIVE LOGITS
    of
    2.47
     There
    2.17
    es
    2.16
    ︓
    2.03
     et
    1.92
     solteiro
    1.88
     Does
    1.86
     a
    1.82
     DOES
    1.81
     We
    1.80
    Activations Density 0.027%

    No Known Activations