© 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. 11023
    Prev
    Next
    INDEX
    Explanations

    programming languages and file extensions

    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
    LIO
    -1.01
    мов
    -0.99
     گفت
    -0.93
    福祉
    -0.92
     evolução
    -0.91
     relacionamento
    -0.90
     একটি
    -0.90
     subsequent
    -0.89
     Ph
    -0.87
     値下げ
    -0.87
    POSITIVE LOGITS
     équip
    1.10
    sistence
    1.09
     they
    1.03
     disponibilités
    0.99
    verstanden
    0.94
     coû
    0.93
    وازم
    0.91
    aspx
    0.90
     équi
    0.88
    compati
    0.88
    Activations Density 0.001%

    No Known Activations