© 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. 37791
    Prev
    Next
    INDEX
    Explanations

    ranking numbers, positions, or orders

    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
     both
    -2.55
    Both
    -1.74
     दोनों
    -1.57
     Both
    -1.55
    both
    -1.45
     BOTH
    -1.35
     оба
    -1.23
    BOTH
    -1.23
    どちらも
    -1.23
     både
    -1.22
    POSITIVE LOGITS
    fourth
    1.41
    Fourth
    1.23
     quatrième
    1.21
    第四
    1.16
     четвер
    1.10
     Fourth
    1.06
     fourth
    1.05
    dania
    0.88
    estra
    0.84
     الرابع
    0.84
    Activations Density 0.106%

    No Known Activations