© 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. 103337
    Prev
    Next
    INDEX
    Explanations

    in compliance or as specified

    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
     not
    -1.13
     quaisquer
    -1.01
     навіть
    -0.97
     even
    -0.96
     any
    -0.96
    Nép
    -0.96
     but
    -0.95
     añadió
    -0.92
    Semua
    -0.91
    Mesmo
    -0.89
    POSITIVE LOGITS
     already
    1.27
    already
    1.23
     consens
    1.13
    Already
    1.10
     уже
    1.09
     expressly
    1.07
     специально
    1.05
     previously
    1.03
     agreed
    1.02
    renderItem
    1.02
    Activations Density 0.117%

    No Known Activations