© 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. 38340
    Prev
    Next
    INDEX
    Explanations

    names of artists, writers, directors

    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
    }
    -1.28
    孃
    -1.26
     Augenblick
    -1.26
     Konzert
    -1.23
    Israël
    -1.21
    eterangan
    -1.20
    ఛ
    -1.18
     音乐
    -1.18
     côtés
    -1.17
     jūsų
    -1.16
    POSITIVE LOGITS
     if
    1.59
     at
    1.47
     even
    1.44
     one
    1.28
     it
    1.28
     potencial
    1.24
     by
    1.22
    ＠
    1.21
     extracto
    1.20
     especially
    1.19
    Activations Density 0.149%

    No Known Activations