© 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. 35983
    Prev
    Next
    INDEX
    Explanations

    after pronouns and nouns

    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
     viso
    -0.91
     wszystkim
    -0.88
    忙しい
    -0.85
     magnific
    -0.85
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -0.84
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.83
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.82
    嚷
    -0.82
    あの
    -0.82
    ↵↵↵↵↵↵↵↵↵↵
    -0.82
    POSITIVE LOGITS
     with
    1.39
     as
    1.19
     rồi
    0.94
    떻
    0.93
    って思
    0.93
     природа
    0.91
     hoping
    0.91
    彗
    0.90
    欲望
    0.90
    逡
    0.89
    Activations Density 0.009%

    No Known Activations