© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119034
    Prev
    Next
    INDEX
    Explanations

    software names and technical terms

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

    technical terms and identifiers related to CAD software, programming, and computational tools (like FreeCAD, OpenFOAM, class names, and function names).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    鹪
    -1.46
     illustrationer
    -1.45
     搞笑
    -1.38
    chläge
    -1.34
    ración
    -1.34
     behandel
    -1.31
    屃
    -1.31
    
    -1.30
     naš
    -1.30
    anjutan
    -1.30
    POSITIVE LOGITS
     a
    2.02
     ,
    1.41
    </
    1.39
     out
    1.39
    }
    1.35
     to
    1.35
    k
    1.34
     de
    1.31
     >
    1.30
    <i>
    1.28
    Activations Density 0.032%

    No Known Activations