© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65091
    Prev
    Next
    INDEX
    Explanations

    "Smart Technology", "brushless short", "vertebral fractures"

    np_acts-logits-general · gemini-2.5-flash-lite

    terminology related to remote control (RC) aircraft and hobby electronics.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     profeta
    -0.73
     業
    -0.72
    adesivo
    -0.72
     Assignee
    -0.71
     variar
    -0.70
    Modifier
    -0.69
     миру
    -0.68
    Appellant
    -0.67
     diversa
    -0.67
     лы
    -0.67
    POSITIVE LOGITS
     Carden
    0.78
     Kol
    0.77
     CFD
    0.75
    Contin
    0.75
    дарю
    0.73
     kol
    0.73
     Baum
    0.72
    蠡
    0.71
    angerie
    0.71
     aeruginosa
    0.70
    Activations Density 0.011%

    No Known Activations