© 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. 87118
    Prev
    Next
    INDEX
    Explanations

    my daughter's shower head

    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
     ahora
    -1.57
     valamint
    -1.52
     sowie
    -1.52
    TIE
    -1.40
     времена
    -1.40
    ADVANCED
    -1.38
     amd
    -1.38
     “
    -1.37
     enchanting
    -1.37
    ACF
    -1.34
    POSITIVE LOGITS
    4
    1.66
    ーズン
    1.59
     هاي
    1.45
    ſſel
    1.45
     feststellen
    1.35
    對於
    1.34
    When
    1.34
    之後
    1.31
    漫畫
    1.30
    ዣ
    1.30
    Activations Density 0.046%

    No Known Activations