© 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. 22-GEMMASCOPE-RES-131K
    4. 68410
    Prev
    Next
    INDEX
    Explanations

    finding closest among sorted array

    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_22/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
     ene
    -1.00
     Tuhan
    -0.99
     än
    -0.95
     två
    -0.93
     enfermera
    -0.90
    ensure
    -0.89
    odeon
    -0.89
    geladen
    -0.89
    də
    -0.89
     ê
    -0.89
    POSITIVE LOGITS
     determining
    1.09
    Поэтому
    1.00
     protecting
    0.98
    自身の
    0.96
     whose
    0.96
     those
    0.94
     providing
    0.92
     entering
    0.92
    ljeno
    0.92
     there
    0.91
    Activations Density 0.002%

    No Known Activations