© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22842
    Prev
    Next
    INDEX
    Explanations

    babes and chicks

    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
    Negative Logits
    ”:
    -2.88
    !”
    -2.64
    ᎑
    -2.42
    焄
    -2.41
    鱘
    -2.36
    ...”
    -2.36
    梘
    -2.34
     ominous
    -2.33
    晸
    -2.30
    蠵
    -2.30
    POSITIVE LOGITS
    Compared
    2.66
    )
    2.38
    未だ
    2.33
    
    2.30
    geſ
    2.27
    赃
    2.23
    かげ
    2.22
     кровь
    2.19
    ほうが
    2.17
    dijual
    2.16
    Activations Density 0.002%

    No Known Activations