© 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. 73892
    Prev
    Next
    INDEX
    Explanations

    programming namespaces

    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
     because
    -1.13
     this
    -1.12
     from
    -1.07
     with
    -0.99
     which
    -0.99
     even
    -0.97
     it
    -0.93
     after
    -0.91
     until
    -0.88
     tailored
    -0.88
    POSITIVE LOGITS
     namespace
    1.30
    namespace
    1.18
    gebracht
    1.05
    ⁷
    1.02
    moreland
    1.01
    fällig
    0.99
    suo
    0.94
     ROBERT
    0.94
     BEAUTIFUL
    0.93
    increasing
    0.93
    Activations Density 0.041%

    No Known Activations