© 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. 10-GEMMASCOPE-RES-131K
    4. 20459
    Prev
    Next
    INDEX
    Explanations

    cadence, intonation, bpm

    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_10/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
    </h3>
    -3.31
    ﱠ
    -2.47
    ズニー
    -2.47
    敺
    -2.45
    怍
    -2.42
     einzigen
    -2.34
     estekak
    -2.28
    锱
    -2.25
     {
    -2.23
     suited
    -2.20
    POSITIVE LOGITS
    </b>
    2.61
     glimmer
    2.08
    yayım
    2.06
    könyv
    1.97
    嗄
    1.96
    困惑
    1.92
    ܜ
    1.91
    侂
    1.90
    
    1.84
    躯
    1.83
    Activations Density 0.005%

    No Known Activations