© 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. 22-GEMMASCOPE-RES-131K
    7. 15276
    Prev
    Next
    INDEX
    Explanations

    conditional terminators

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

    conditional branching constructs in programming code, particularly when handling termination conditions.

    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_22/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
    exactly
    -1.04
     exactly
    -1.04
     indivíduos
    -1.02
     estableció
    -0.92
     leña
    -0.90
     EXACTLY
    -0.87
    dika
    -0.85
     poucos
    -0.85
     omtrent
    -0.85
     nästan
    -0.84
    POSITIVE LOGITS
    matmul
    0.90
    stination
    0.83
    écnicas
    0.83
     if
    0.82
    IRUS
    0.82
     for
    0.81
     ins
    0.79
    原创
    0.79
    降低
    0.77
    知る
    0.77
    Activations Density 0.002%

    No Known Activations