© 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. 66608
    Prev
    Next
    INDEX
    Explanations

    and followed by conjunctions or conclusions

    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
     évalu
    -1.12
    あくまで
    -1.09
    贬
    -1.04
    😊
    -1.04
    々と
    -1.02
    Prés
    -1.02
     ché
    -1.00
    🐸
    -0.98
     après
    -0.97
    藜
    -0.97
    POSITIVE LOGITS
     it
    1.62
     should
    1.52
     would
    1.20
     therefore
    1.19
     moreover
    1.14
    它的
    1.09
     consequences
    1.06
     consequently
    1.05
    これを
    1.03
     even
    1.02
    Activations Density 0.024%

    No Known Activations