© 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. 25340
    Prev
    Next
    INDEX
    Explanations

    first-person pronoun I

    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
     is
    -1.78
     because
    -1.55
    を
    -1.54
    D
    -1.52
     possibly
    -1.49
     dramatically
    -1.48
    ↵↵
    -1.47
     after
    -1.45
     were
    -1.41
    、
    -1.41
    POSITIVE LOGITS
    を書く
    1.62
    
    1.60
    ができます
    1.58
    の準備
    1.55
    ことにしました
    1.52
    に入れる
    1.51
    の概要
    1.50
    の魅力
    1.48
    を変更
    1.48
    ⚣
    1.47
    Activations Density 0.166%

    No Known Activations