© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34871
    Prev
    Next
    INDEX
    Explanations

    code construct markers

    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
    lampen
    -0.96
    書の
    -0.91
    ynı
    -0.90
     заниматься
    -0.88
    prende
    -0.85
    şağı
    -0.85
    gencias
    -0.84
    tividade
    -0.84
    utenants
    -0.82
    yors
    -0.82
    POSITIVE LOGITS
    OrNull
    0.84
    ILLON
    0.82
     đây
    0.81
     bloß
    0.79
    蜒
    0.78
    IEU
    0.77
     nostalgic
    0.75
     questione
    0.75
     vâ
    0.75
     uży
    0.74
    Activations Density 0.002%

    No Known Activations