© 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. 34-GEMMASCOPE-RES-131K
    4. 23596
    Prev
    Next
    INDEX
    Explanations

    contrast or contrasting

    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_34/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
     cóc
    -1.08
    ⾒
    -1.02
    Cantidad
    -1.00
    いが
    -0.99
    Filt
    -0.96
     cantantes
    -0.94
     convidados
    -0.94
    いかがでしたか
    -0.94
    đèn
    -0.93
    Wz
    -0.93
    POSITIVE LOGITS
     contrast
    2.41
    contrast
    2.23
     Contrast
    2.17
     stark
    1.99
    Contrast
    1.78
     контра
    1.74
     contrasts
    1.74
     contraste
    1.55
     Contra
    1.42
    ingly
    1.36
    Activations Density 0.012%

    No Known Activations