© 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. 22-GEMMASCOPE-RES-131K
    7. 24924
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    +:+
    -1.14
    yors
    -1.13
    Ő
    -1.02
    GetSize
    -0.98
    )++;
    -0.97
    ICION
    -0.95
    ılan
    -0.95
    ısı
    -0.94
     potensi
    -0.93
    convertView
    -0.93
    POSITIVE LOGITS
    믄
    1.15
     funzionalità
    1.10
     varietà
    1.08
     zugel
    1.08
     numai
    1.05
     decorazione
    1.04
     partecipare
    1.03
     rekomendasi
    1.03
    읽
    1.03
     заявил
    1.02
    Activations Density 0.001%

    No Known Activations