© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25907
    Prev
    Next
    INDEX
    Explanations

    being + past participle verbs

    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
    や
    -1.46
     was
    -1.38
     (
    -1.37
     also
    -1.36
     actually
    -1.14
     فإن
    -1.13
     alebo
    -1.12
    ۜ
    -1.11
    もあり
    -1.11
     fok
    -1.10
    POSITIVE LOGITS
    為に
    1.91
    久し
    1.81
    際に
    1.77
    際には
    1.60
     habiendo
    1.57
    感じが
    1.56
    で見る
    1.56
     It
    1.53
    ふと
    1.51
    マジで
    1.49
    Activations Density 0.039%

    No Known Activations