© 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. 9667
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
     also
    -1.63
     only
    -1.58
     always
    -1.33
     still
    -1.31
    もあって
    -1.30
    
    -1.27
    。』
    -1.13
     mainly
    -1.13
     chiefly
    -1.11
    もあり
    -1.06
    POSITIVE LOGITS
    corrhi
    1.25
     ebbe
    1.17
    譴
    1.14
    之家
    1.13
     dejar
    1.07
    bruh
    1.02
    prender
    0.98
     Andere
    0.98
     ese
    0.98
    congrats
    0.96
    Activations Density 0.041%

    No Known Activations