© 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. 34-GEMMASCOPE-RES-131K
    7. 98785
    Prev
    Next
    INDEX
    Explanations

    more or better

    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
     rất
    -1.20
     uite
    -1.16
     aucune
    -1.13
    🛀
    -1.11
    RuntimeObject
    -1.10
    Demografia
    -1.09
    циональный
    -1.09
     aparcamiento
    -1.07
    髯
    -1.05
     весьма
    -1.04
    POSITIVE LOGITS
     more
    7.28
     better
    5.22
     более
    4.47
     יותר
    4.00
     lebih
    3.92
     bardziej
    3.91
    更
    3.88
     clearer
    3.80
    更加
    3.59
     greater
    3.52
    Activations Density 0.303%

    No Known Activations