© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20666
    Prev
    Next
    INDEX
    Explanations

    division by zero or incrementing

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

    while loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Św
    0.42
    CBC
    0.40
     Solicitor
    0.39
    MRT
    0.39
     पीपल
    0.38
     ஒன்றாகும்
    0.38
    សា
    0.38
    巉
    0.38
    竦
    0.38
    <unused39>
    0.38
    POSITIVE LOGITS
     while
    0.65
     mientras
    0.57
    while
    0.54
     for
    0.52
     mentre
    0.50
     nigdy
    0.49
     every
    0.48
     предъ
    0.47
     terwijl
    0.47
     enquanto
    0.46
    Activations Density 0.000%

    No Known Activations