© 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. 40315
    Prev
    Next
    INDEX
    Explanations

    placeholder phrases

    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
     cinto
    -0.85
    complished
    -0.84
    ciąż
    -0.83
    身邊
    -0.83
    szám
    -0.82
     représenté
    -0.81
    embang
    -0.78
    halloween
    -0.78
    他にも
    -0.77
     พื้น
    -0.77
    POSITIVE LOGITS
     too
    1.04
     тоже
    0.98
     another
    0.91
     Kluwer
    0.91
     ebenfalls
    0.88
    return
    0.88
    tilde
    0.83
    value
    0.81
    NAN
    0.79
    斐
    0.77
    Activations Density 0.035%

    No Known Activations