© 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. 820
    Prev
    Next
    INDEX
    Explanations

    finding or searching

    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
    glor
    -0.85
    Sementara
    -0.76
    willing
    -0.72
     يس
    -0.68
    ienna
    -0.67
     longe
    -0.66
     Gelen
    -0.65
    呱
    -0.65
     gehabt
    -0.64
     μπα
    -0.64
    POSITIVE LOGITS
    FIND
    1.54
     find
    1.44
     Find
    1.42
    contrar
    1.40
     Finder
    1.39
     retrouver
    1.38
     FIND
    1.37
     findings
    1.34
    Finder
    1.34
     findViewById
    1.31
    Activations Density 0.031%

    No Known Activations