© 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. 22-GEMMASCOPE-RES-131K
    7. 36329
    Prev
    Next
    INDEX
    Explanations

    chemical characterization Johan Maurits Q:

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

    programming file header and syntax elements, particularly in C++ code.

    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_22/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
     they
    -1.44
    必要
    -1.09
     then
    -1.05
    需要
    -1.01
     them
    -1.00
     others
    -0.99
     someone
    -0.96
     aufgrund
    -0.95
     already
    -0.93
    いけ
    -0.91
    POSITIVE LOGITS
    ucous
    1.09
     Loon
    1.03
     UIT
    1.03
    faster
    1.02
    sprechen
    1.02
     áng
    0.99
    ragende
    0.99
     társ
    0.98
    ⚘
    0.96
    bemos
    0.94
    Activations Density 0.001%

    No Known Activations