© 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. 73642
    Prev
    Next
    INDEX
    Explanations

    who 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
     mentre
    -1.12
    glit
    -1.07
     they
    -1.05
     while
    -1.03
     jugó
    -1.03
     demostrar
    -1.02
     hvilke
    -1.02
     our
    -1.02
     it
    -1.01
    citrus
    -1.00
    POSITIVE LOGITS
     among
    1.03
    缡
    1.00
     inſ
    0.97
    ksessa
    0.96
     คุณ
    0.96
    𖤍
    0.96
    今回の
    0.95
    iseite
    0.94
    וּ
    0.94
     такого
    0.93
    Activations Density 0.027%

    No Known Activations