© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14786
    Prev
    Next
    INDEX
    Explanations

    cryo- or -ogenic

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

    words related to cryogenic technology and freezing processes.

    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_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
     are
    -2.14
     forcefully
    -1.99
     Herausgeber
    -1.96
     minimizes
    -1.91
    色が
    -1.87
    лись
    -1.84
    荩
    -1.84
    initWithFrame
    -1.83
    痦
    -1.80
     expressly
    -1.79
    POSITIVE LOGITS
    紲
    2.13
    ↵
    2.11
    ,
    1.89
     difficiles
    1.88
    
    1.77
    
    1.73
     bedienen
    1.73
    สี
    1.72
    ’
    1.71
     sosial
    1.65
    Activations Density 0.016%

    No Known Activations