© 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. 93161
    Prev
    Next
    INDEX
    Explanations

    third-person pronouns and possessives

    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
     desn
    -1.00
    Soorten
    -0.95
    emptions
    -0.91
    Bereich
    -0.90
     revela
    -0.90
    ૫
    -0.89
    getComponent
    -0.88
     compris
    -0.87
     bunun
    -0.85
    Abbiamo
    -0.84
    POSITIVE LOGITS
     his
    2.52
     their
    2.27
     he
    1.87
     him
    1.71
     hänen
    1.53
     его
    1.44
     her
    1.43
     she
    1.41
     jego
    1.40
     suoi
    1.30
    Activations Density 0.087%

    No Known Activations