© 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. 39128
    Prev
    Next
    INDEX
    Explanations

    Japanese female skin penetration

    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
     They
    -3.19
    if
    -2.56
     ſta
    -2.44
     鐵
    -2.39
     ſy
    -2.30
    ization
    -2.22
    Ideally
    -2.19
     Это
    -2.09
    Thus
    -2.08
     Ukraina
    -2.08
    POSITIVE LOGITS
     they
    4.34
    ↵
    2.78
    、『
    2.34
    ’
    2.30
    ,.
    2.28
    ：“
    2.25
     haupts
    2.19
    啬
    2.16
     years
    2.13
     a
    2.11
    Activations Density 0.001%

    No Known Activations