© 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. 10-GEMMASCOPE-RES-131K
    7. 11617
    Prev
    Next
    INDEX
    Explanations

    technical documentation and questions

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

    technical or gaming-related terminology, particularly words related to game mechanics, military equipment, and technical specifications.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    the presence of specialized technical or gaming jargon and numeric specifications.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     after
    -1.66
    செ
    -1.45
     bribery
    -1.40
     should
    -1.37
     from
    -1.33
     Germany
    -1.32
     Italy
    -1.30
    fstream
    -1.27
     if
    -1.25
    🍕
    -1.21
    POSITIVE LOGITS
    秶
    1.47
     effectuer
    1.34
     jusqu
    1.34
    those
    1.34
    until
    1.31
    Ӕ
    1.23
    甴
    1.23
    Until
    1.23
    甚至
    1.22
     getUserId
    1.21
    Activations Density 0.005%

    No Known Activations