© 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. 111036
    Prev
    Next
    INDEX
    Explanations

    including files or content

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

    the word "include" in code contexts, particularly in import statements, file inclusions, and configuration directives.

    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
    ”
    -2.36
    </i>
    -2.27
    of
    -2.27
    ”,
    -1.91
     этого
    -1.91
    """
    -1.90
    ,”
    -1.88
    E
    -1.86
    <i>
    -1.84
    de
    -1.75
    POSITIVE LOGITS
    dzić
    2.06
    ﻒ
    1.80
    CurtirCurtir
    1.63
    侂
    1.60
     bestaan
    1.59
    akterysty
    1.56
    
    1.55
     ⓒ
    1.55
     hlm
    1.55
     ngan
    1.53
    Activations Density 0.033%

    No Known Activations