© 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. 22-GEMMASCOPE-RES-131K
    7. 67581
    Prev
    Next
    INDEX
    Explanations

    programming code and syntax

    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
     शुर
    -1.09
    ská
    -1.02
    datable
    -0.97
     Erscheinung
    -0.96
    );\
    -0.95
    }),
    -0.93
     Merkmale
    -0.93
    برى
    -0.92
    izm
    -0.89
     those
    -0.89
    POSITIVE LOGITS
     cristi
    1.13
     Conſ
    1.05
    ,
    1.04
     Barrera
    1.03
    </strong>
    1.02
    hode
    1.02
    usalem
    1.01
     EXCELL
    0.99
    </b>
    0.98
    </i>
    0.98
    Activations Density 0.012%

    No Known Activations