© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99555
    Prev
    Next
    INDEX
    Explanations

    HyperX, cost of, strategy for

    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
    シック
    -0.77
     enge
    -0.77
    깁
    -0.75
     offrire
    -0.75
     dürfen
    -0.74
     superbly
    -0.73
    懼
    -0.73
    菴
    -0.73
     its
    -0.71
     tacit
    -0.71
    POSITIVE LOGITS
    uskas
    1.00
    क्षित
    0.91
     ADB
    0.90
    AXIS
    0.87
     çocu
    0.82
    übers
    0.82
     különböző
    0.82
     OM
    0.82
    hadap
    0.81
    tocks
    0.80
    Activations Density 0.002%

    No Known Activations