© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93244
    Prev
    Next
    INDEX
    Explanations

    if necessary or possible

    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
     if
    -2.50
     ако
    -1.55
     если
    -1.54
     якщо
    -1.48
    IfNeeded
    -1.43
     nếu
    -1.37
     اگر
    -1.31
     unless
    -1.26
     dacă
    -1.24
    如果
    -1.21
    POSITIVE LOGITS
    ande
    0.99
    ə
    0.90
    ura
    0.85
    …………………………………………
    0.83
    ի
    0.82
    стью
    0.81
    uegos
    0.81
    IMENTO
    0.80
    uc
    0.80
    </tr>
    0.80
    Activations Density 0.057%

    No Known Activations