© 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. 73695
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by common 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
     this
    -1.74
     will
    -1.63
     using
    -1.52
     these
    -1.52
     only
    -1.50
     with
    -1.49
     for
    -1.37
     including
    -1.34
     other
    -1.29
     while
    -1.27
    POSITIVE LOGITS
     imprimer
    1.64
     corriger
    1.52
     álcool
    1.44
     fermer
    1.40
     assise
    1.38
     recommandée
    1.37
     verbind
    1.34
     alho
    1.32
     ſou
    1.30
     geene
    1.29
    Activations Density 0.285%

    No Known Activations