© 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. 70460
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and conjunctions

    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
     is
    -1.36
     are
    -1.15
     हैं
    -0.95
     doesnt
    -0.91
     आहे
    -0.91
     đang
    -0.89
    当前
    -0.87
     bestehenden
    -0.86
    하는
    -0.85
    Occupied
    -0.83
    POSITIVE LOGITS
     was
    2.33
     eventually
    1.45
     وكان
    1.38
    もあった
    1.38
    だったので
    1.37
    だった
    1.34
     было
    1.34
     were
    1.34
    后来
    1.33
     now
    1.31
    Activations Density 0.108%

    No Known Activations