© 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. 79540
    Prev
    Next
    INDEX
    Explanations

    again and in other languages

    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
     what
    -0.89
     that
    -0.87
     both
    -0.85
     encaje
    -0.79
     promotes
    -0.79
     well
    -0.78
     avoiding
    -0.78
     reflexionar
    -0.78
     these
    -0.78
     intense
    -0.77
    POSITIVE LOGITS
     again
    1.29
    今度は
    1.26
     nuovamente
    1.02
     ayur
    0.98
    again
    0.96
    它
    0.96
     erneut
    0.92
     novamente
    0.91
    europa
    0.89
     снова
    0.85
    Activations Density 0.041%

    No Known Activations