© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99799
    Prev
    Next
    INDEX
    Explanations

    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_34/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
     mortem
    -0.95
    bably
    -0.92
     obtenir
    -0.91
    uing
    -0.90
     améliorer
    -0.90
    andering
    -0.90
    燃烧
    -0.89
    𓁹
    -0.88
    modèle
    -0.88
    establishing
    -0.87
    POSITIVE LOGITS
    ness
    1.00
     incorrectly
    0.87
     Poto
    0.86
    쌍
    0.85
    just
    0.83
    raw
    0.82
    天津
    0.81
    ésultat
    0.79
     уже
    0.79
    zeciw
    0.78
    Activations Density 0.104%

    No Known Activations