© 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. 113518
    Prev
    Next
    INDEX
    Explanations

    RT followed by abbreviations and technical terms

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

    the abbreviation "RT" (often as part of technical identifiers, variable names, or acronyms in code and technical contexts).

    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
    ).
    -2.34
     —
    -2.30
    ),
    -2.14
    StoryboardSegue
    -2.06
     […]
    -2.06
    𝗸
    -2.05
    </h2>
    -2.03
     если
    -2.02
     auftreten
    -2.02
    ная
    -2.00
    POSITIVE LOGITS
    廰
    2.64
    錞
    2.61
    𓆜
    2.58
    廨
    2.56
    鈁
    2.55
    齮
    2.48
     現貨
    2.45
     kimdir
    2.41
     tarefa
    2.39
    丏
    2.39
    Activations Density 0.016%

    No Known Activations