© 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. 10-GEMMASCOPE-RES-131K
    7. 61323
    Prev
    Next
    INDEX
    Explanations

    intensifiers and modifiers

    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_10/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
     andere
    -1.43
     still
    -1.42
    </tbody>
    -1.38
     a
    -1.38
     always
    -1.37
    “
    -1.36
    沙发
    -1.31
    =}
    -1.29
     way
    -1.28
    ani
    -1.28
    POSITIVE LOGITS
     Pristup
    1.76
     также
    1.68
    Also
    1.41
     також
    1.40
     też
    1.36
     también
    1.36
    оны
    1.34
    lamó
    1.31
    大きい
    1.29
     tatuagens
    1.28
    Activations Density 0.191%

    No Known Activations