© 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. 45304
    Prev
    Next
    INDEX
    Explanations

    ports and network status

    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
     both
    -0.83
     English
    -0.81
     any
    -0.81
     väga
    -0.81
     best
    -0.81
     felt
    -0.78
     Please
    -0.77
    igera
    -0.75
    wstring
    -0.75
     Aufenthalt
    -0.75
    POSITIVE LOGITS
     céramique
    0.90
    ߘ
    0.89
    recently
    0.89
    LISTEN
    0.88
     vyu
    0.88
     Etihad
    0.88
    apparently
    0.88
     LISTEN
    0.87
     morceaux
    0.86
     ultime
    0.85
    Activations Density 0.081%

    No Known Activations