© 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. 9377
    Prev
    Next
    INDEX
    Explanations

    German and Dutch verbs, followed by auxiliaries or direct objects

    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
    Ꮋ
    -0.98
     Houston
    -0.91
     ONLY
    -0.90
    šie
    -0.90
    րան
    -0.89
     spoon
    -0.88
    香港
    -0.88
     Because
    -0.87
    角度
    -0.85
     are
    -0.85
    POSITIVE LOGITS
     been
    1.52
     fått
    1.11
     chrétien
    1.02
     curé
    0.98
    痛い
    0.98
    带来了
    0.97
    носит
    0.96
    lihatkan
    0.95
     everything
    0.94
    Tried
    0.92
    Activations Density 0.002%

    No Known Activations