© 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. 118340
    Prev
    Next
    INDEX
    Explanations

    shapes of objects

    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
    camps
    -0.84
    つまり
    -0.81
     위한
    -0.78
    ArgsConstructor
    -0.77
     of
    -0.76
    引起了
    -0.76
    rss
    -0.72
    beginPath
    -0.71
    циональный
    -0.70
     constitutive
    -0.69
    POSITIVE LOGITS
     rectangular
    1.09
    товых
    0.93
     headed
    0.90
    headed
    0.90
     square
    0.90
    rectangular
    0.90
    kamers
    0.86
    льные
    0.85
     profiled
    0.84
     shaped
    0.84
    Activations Density 0.033%

    No Known Activations