© 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. 107775
    Prev
    Next
    INDEX
    Explanations

    distributed on an AS IS

    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
     heaven
    -0.77
     Heaven
    -0.75
     politi
    -0.75
    ABETH
    -0.74
    Harvard
    -0.72
    Heaven
    -0.71
    dań
    -0.66
     Kapit
    -0.65
    Поли
    -0.65
    ılmış
    -0.65
    POSITIVE LOGITS
     getPath
    0.72
     פני
    0.66
    EMBER
    0.65
    istre
    0.65
    Invariant
    0.65
     funcionar
    0.65
    ዮ
    0.64
    ))^
    0.64
    arpa
    0.63
     apunta
    0.63
    Activations Density 0.094%

    No Known Activations