© 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. 34-GEMMASCOPE-RES-131K
    4. 102990
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
     Specifically
    -0.77
    라는
    -0.76
     ober
    -0.75
    printable
    -0.75
     Jamal
    -0.72
    Artikel
    -0.72
    ślę
    -0.71
    tivos
    -0.70
     fascia
    -0.70
     específicamente
    -0.69
    POSITIVE LOGITS
    宵
    0.74
     répondit
    0.73
    也很
    0.73
     PEP
    0.72
     nonsense
    0.72
    downe
    0.71
     sure
    0.71
    zza
    0.71
     case
    0.71
     حديث
    0.69
    Activations Density 0.082%

    No Known Activations