© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66129
    Prev
    Next
    INDEX
    Explanations

    count of items

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Britney
    -0.97
    regalo
    -0.96
     miten
    -0.96
     yazılı
    -0.93
     Tamanho
    -0.93
    RISK
    -0.90
     smuggled
    -0.90
     Será
    -0.88
    Kudos
    -0.88
    NextPage
    -0.88
    POSITIVE LOGITS
     kostenlos
    0.95
    rierten
    0.93
     archivi
    0.91
     misiones
    0.90
    หว่าง
    0.88
    ().__
    0.87
     nachdem
    0.86
     ਵਿੱਚ
    0.84
    ha
    0.83
    初め
    0.82
    Activations Density 0.010%

    No Known Activations