© 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. 54424
    Prev
    Next
    INDEX
    Explanations

    classifying words or 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
     itself
    -1.41
    :
    -1.36
     was
    -1.31
     می‌تواند
    -1.23
     of
    -1.07
    了一眼
    -1.05
     is
    -1.04
    </td>
    -1.03
     bane
    -1.00
     or
    -0.96
    POSITIVE LOGITS
     naše
    1.58
     promesas
    1.43
     έχουν
    1.34
     Američ
    1.34
     are
    1.31
     guys
    1.30
    睒
    1.30
     campañas
    1.29
     هستند
    1.28
     üçün
    1.25
    Activations Density 0.034%

    No Known Activations