© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 70335
    Prev
    Next
    INDEX
    Explanations

    technical and legal text beginnings

    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
    Derp
    -0.93
     especí
    -0.91
     cobre
    -0.88
     first
    -0.88
    غيرة
    -0.86
     iaitu
    -0.84
    awarkan
    -0.83
    治安
    -0.83
     fejl
    -0.82
    notag
    -0.81
    POSITIVE LOGITS
    ianos
    0.88
    legel
    0.88
     UGC
    0.88
     annunci
    0.87
     xiv
    0.85
    λης
    0.85
     quo
    0.85
     DHT
    0.85
    かし
    0.83
    栩
    0.82
    Activations Density 0.001%

    No Known Activations