© 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. 98327
    Prev
    Next
    INDEX
    Explanations

    slightly significant

    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
     and
    -0.94
     viewHolder
    -0.91
     興
    -0.90
     både
    -0.88
     especially
    -0.88
     hardly
    -0.88
    ‽
    -0.86
    不但
    -0.85
     eigentlich
    -0.85
     außerdem
    -0.85
    POSITIVE LOGITS
     but
    1.64
     BUT
    1.37
    slightly
    1.26
     pero
    1.24
     SOME
    1.23
    Slightly
    1.22
     लेकिन
    1.20
     некото
    1.17
     slightly
    1.16
     nhưng
    1.16
    Activations Density 0.042%

    No Known Activations