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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84914
    Prev
    Next
    INDEX
    Explanations

    request and javascript code

    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_34/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
     bodyParser
    -0.98
    PERT
    -0.85
     Tomar
    -0.81
    Dime
    -0.78
     TF
    -0.78
    ashimi
    -0.77
     РФ
    -0.75
    ₧
    -0.74
     xu
    -0.73
    воро
    -0.73
    POSITIVE LOGITS
    locals
    1.20
     user
    0.93
     locals
    0.85
    user
    0.83
     エク
    0.82
    MLElement
    0.79
     Request
    0.75
     EKG
    0.74
     requesting
    0.74
     usuario
    0.74
    Activations Density 0.007%

    No Known Activations