© 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. 87168
    Prev
    Next
    INDEX
    Explanations

    3D scanning and related concepts

    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
    sigmoid
    -0.81
     Gnade
    -0.77
     کش
    -0.76
    nard
    -0.76
     indicator
    -0.76
     النوم
    -0.76
    nesia
    -0.75
     periods
    -0.75
    Indicator
    -0.73
    hans
    -0.73
    POSITIVE LOGITS
     scan
    2.13
     scanner
    1.99
     scanning
    1.97
     scans
    1.93
     scanners
    1.89
     scanned
    1.76
    scan
    1.73
     Scanner
    1.61
     Scan
    1.61
    scanner
    1.55
    Activations Density 0.056%

    No Known Activations