© 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. 35732
    Prev
    Next
    INDEX
    Explanations

    common English words

    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
    indeki
    -1.03
    囧
    -0.99
    НОВ
    -0.96
    좇
    -0.96
     YORK
    -0.95
     élevées
    -0.94
     Pradesh
    -0.94
    🪞
    -0.91
    INKS
    -0.91
    bánh
    -0.91
    POSITIVE LOGITS
     defunct
    0.88
    /**
    0.88
    </i>
    0.87
     outras
    0.85
    鰓
    0.85
    虽
    0.84
    """
    0.83
     then
    0.83
     *******
    0.82
    ‌است
    0.81
    Activations Density 0.007%

    No Known Activations