© 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. 65651
    Prev
    Next
    INDEX
    Explanations

    numbers, Unix, medical terms

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

    technology and computing references, especially related to programming, computer systems, and technical documentation.

    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
     auxili
    -0.82
     scalars
    -0.81
     Blanket
    -0.78
    ソニー
    -0.75
     interpreters
    -0.74
    굶
    -0.74
     Educators
    -0.73
     Pras
    -0.73
     blat
    -0.71
    引擎
    -0.71
    POSITIVE LOGITS
     Una
    0.96
     Harvard
    0.82
    aczy
    0.80
    bombs
    0.80
     Manifesto
    0.79
     Ted
    0.79
     Sharon
    0.77
     AR
    0.75
     airline
    0.74
     Amts
    0.73
    Activations Density 0.041%

    No Known Activations