© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15541
    Prev
    Next
    INDEX
    Explanations

    man followed by who or of

    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
    ivät
    -1.02
    miques
    -1.02
    rierten
    -0.96
     their
    -0.94
     buurt
    -0.93
    dė
    -0.93
     it
    -0.92
     other
    -0.91
     jälkeen
    -0.91
     others
    -0.91
    POSITIVE LOGITS
     who
    1.16
    明日は
    1.04
     of
    1.01
     
    0.99
     грун
    0.99
    白い
    0.99
     开发
    0.94
    <!--
    0.94
    Наша
    0.93
    所に
    0.93
    Activations Density 0.023%

    No Known Activations