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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66933
    Prev
    Next
    INDEX
    Explanations

    given names and surnames

    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_22/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
     only
    -1.17
    These
    -0.98
     similar
    -0.93
     heightened
    -0.90
    This
    -0.88
     may
    -0.88
     solely
    -0.87
    Other
    -0.85
     less
    -0.85
     notable
    -0.84
    POSITIVE LOGITS
    boring
    0.96
    scrape
    0.93
     chaussures
    0.92
    }}=
    0.91
    athered
    0.91
     LONG
    0.89
     Schuhe
    0.88
    旆
    0.86
    aning
    0.86
     parfü
    0.85
    Activations Density 0.071%

    No Known Activations